{"family": "online_enron_intent_neg", "id": "product-blind-v2-00001", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2144", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2144", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00002", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1241", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1241", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00003", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-760", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L760", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00004", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-303", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L303", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00005", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-717", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L717", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00006", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3387076693", "sourceURL": "https://github.com/huggingface/datasets/issues/7756", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00007", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-6268", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1024", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00008", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6378", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1112", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00009", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1146", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1146", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00010", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2563364199", "sourceURL": "https://github.com/huggingface/datasets/issues/7194", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00011", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-690", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L690", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00012", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3503446288", "sourceURL": "https://github.com/huggingface/datasets/issues/7813", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00013", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7559", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1317", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00014", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1789782693-comment-6", "sourceURL": "https://github.com/huggingface/datasets/issues/6007", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00015", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1846205216", "sourceURL": "https://github.com/huggingface/datasets/issues/6142", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00016", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1567", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1567", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00017", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-16166", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2774", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00018", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-509", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L509", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_32", "id": "product-blind-v2-00019", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7503", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1307", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00020", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-515", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L515", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00021", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-290", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L290", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00022", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14884", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2553", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00023", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2915233248-comment-2", "sourceURL": "https://github.com/huggingface/datasets/issues/7447", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00024", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6668283", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6668283", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00025", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2334", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=392", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00026", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-3672", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-3672", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00027", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1872285153", "sourceURL": "https://github.com/huggingface/datasets/issues/6193", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00028", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2306", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2306", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00029", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1488", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1488", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00030", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-466", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L466", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00031", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3498534596-comment-5", "sourceURL": "https://github.com/huggingface/datasets/issues/7804", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00032", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4491", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=781", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00033", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-22764", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-22764", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_15", "id": "product-blind-v2-00034", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16846", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2781", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00035", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1234", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1234", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00036", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2327", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2327", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00037", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6974", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1232", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00038", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1827054143", "sourceURL": "https://github.com/huggingface/datasets/issues/6097", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00039", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1215", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1215", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00040", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-742", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L742", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00041", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2776929268", "sourceURL": "https://github.com/huggingface/datasets/issues/7364", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00042", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7726", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1344", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00043", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2323", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2323", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_19", "id": "product-blind-v2-00044", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11922", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2084", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00045", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-960", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L960", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00046", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1094", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1094", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00047", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15966", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2731", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00048", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-2917", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-2917", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00049", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-333", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L333", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00050", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2378424349", "sourceURL": "https://github.com/huggingface/datasets/issues/7005", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00051", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-940", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L940", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00052", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1090", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1090", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00053", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6684733", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6684733", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00054", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16713", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2758", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00055", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6097074", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6097074", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00056", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-290", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L290", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00057", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-27627", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-27627", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00058", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1606", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1606", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00059", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1744009032", "sourceURL": "https://github.com/huggingface/datasets/issues/5927", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00060", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-34211", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-34211", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00061", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2282", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2282", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00062", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2382976738", "sourceURL": "https://github.com/huggingface/datasets/issues/7013", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00063", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2069922151", "sourceURL": "https://github.com/huggingface/datasets/issues/6568", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00064", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1057", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1057", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00065", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-468", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L468", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00066", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-46432", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-46432", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00067", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-968", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L968", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00068", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-803", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L803", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00069", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-518", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L518", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00070", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1736", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1736", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00071", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1174", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1174", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00072", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3212", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=543", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00073", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7257", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1277", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_53", "id": "product-blind-v2-00074", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10827", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1891", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00075", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2981687450", "sourceURL": "https://github.com/huggingface/datasets/issues/7506", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00076", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1069", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1069", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00077", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-644", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L644", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00078", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-6544", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-6544", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00079", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13513", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2316", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00080", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-713", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L713", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00081", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-2960679", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/2960679", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00082", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-2769739", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/2769739", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": null, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00083", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-32804", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-32804", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00084", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2523129465", "sourceURL": "https://github.com/huggingface/datasets/issues/7147", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00085", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-853", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L853", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00086", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1149", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1149", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_34", "id": "product-blind-v2-00087", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-292", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=53", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00088", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2083708521", "sourceURL": "https://github.com/huggingface/datasets/issues/6597", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_3", "id": "product-blind-v2-00089", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2163", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=355", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00090", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2245", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2245", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_32", "id": "product-blind-v2-00091", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8347", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1448", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00092", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-27502", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-27502", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_0", "id": "product-blind-v2-00093", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5427", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=945", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00094", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-341", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L341", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00095", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13177", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2261", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_58", "id": "product-blind-v2-00096", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11476", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2010", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00097", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1844511519", "sourceURL": "https://github.com/huggingface/datasets/issues/6133", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00098", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1078", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1078", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00099", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-5612875", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/5612875", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00100", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2546710631", "sourceURL": "https://github.com/huggingface/datasets/issues/7168", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00101", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-4429849", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/4429849", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00102", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-765", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L765", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00103", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1224", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1224", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00104", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-618", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L618", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_43", "id": "product-blind-v2-00105", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-4985", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=810", "stratumAvailable": 4, "stratumSelected": 4, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00106", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4848", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=833", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00107", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-811", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L811", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00108", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2886032571", "sourceURL": "https://github.com/huggingface/datasets/issues/7427", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00109", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-953", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L953", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00110", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2860947582", "sourceURL": "https://github.com/huggingface/datasets/issues/7413", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00111", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-868", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L868", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00112", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-810", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L810", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00113", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1872598223-comment-6", "sourceURL": "https://github.com/huggingface/datasets/issues/6194", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00114", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-15456", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2531", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00115", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16780", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2772", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00116", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-895", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L895", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_3", "id": "product-blind-v2-00117", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-967", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=169", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00118", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8585", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1489", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00119", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1716770394", "sourceURL": "https://github.com/huggingface/datasets/issues/5875", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_23", "id": "product-blind-v2-00120", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2673", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=447", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00121", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13929", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2391", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00122", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1665", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1665", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00123", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-158", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L158", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00124", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-8474", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1394", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00125", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1506", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1506", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00126", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2089230766", "sourceURL": "https://github.com/huggingface/datasets/issues/6603", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00127", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-942", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L942", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_31", "id": "product-blind-v2-00128", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2311", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=386", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00129", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-8866", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-8866", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00130", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2254", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2254", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00131", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-851", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L851", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00132", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3160544390", "sourceURL": "https://github.com/huggingface/datasets/issues/7627", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00133", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-881", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L881", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00134", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15942", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2725", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00135", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6725", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1187", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00136", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1833", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1833", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00137", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1844991583-comment-6", "sourceURL": "https://github.com/huggingface/datasets/issues/6139", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00138", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-10748", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-10748", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_55", "id": "product-blind-v2-00139", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11812", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2062", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00140", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7258", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1278", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00141", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2406495084", "sourceURL": "https://github.com/huggingface/datasets/issues/7047", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00142", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16729", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2761", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00143", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1720", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1720", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00144", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-8568", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1406", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00145", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-3496362", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/3496362", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00146", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1566", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1566", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00147", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-371", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L371", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_30", "id": "product-blind-v2-00148", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8302", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1441", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00149", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-716", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L716", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00150", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-7360406", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/7360406", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00151", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1187", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1187", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00152", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-980", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L980", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00153", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1799309132", "sourceURL": "https://github.com/huggingface/datasets/issues/6017", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00154", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-23809", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-23809", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00155", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-899", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L899", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00156", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3182745315", "sourceURL": "https://github.com/huggingface/datasets/issues/7650", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00157", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-41645", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-41645", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00158", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1161", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1161", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00159", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3246268635", "sourceURL": "https://github.com/huggingface/datasets/issues/7692", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_57", "id": "product-blind-v2-00160", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-484", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=99", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00161", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-811", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L811", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00162", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1080", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1080", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00163", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-61", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L61", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00164", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-179", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L179", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00165", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4654", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=803", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_36", "id": "product-blind-v2-00166", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9565", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1650", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00167", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-679", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L679", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00168", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-16668", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2860", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00169", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1910275199", "sourceURL": "https://github.com/huggingface/datasets/issues/6256", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00170", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14417", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2474", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00171", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1217", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1217", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00172", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6220", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1080", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00173", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9014", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1557", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00174", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2158152341", "sourceURL": "https://github.com/huggingface/datasets/issues/6699", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_9", "id": "product-blind-v2-00175", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9940", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1718", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_40", "id": "product-blind-v2-00176", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3785", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=649", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00177", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-923", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L923", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00178", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-574", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L574", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_24", "id": "product-blind-v2-00179", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4799", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=823", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00180", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1365", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1365", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_16", "id": "product-blind-v2-00181", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1830", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=313", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_6", "id": "product-blind-v2-00182", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11969", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2091", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_55", "id": "product-blind-v2-00183", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-13181", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2155", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00184", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7196", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1270", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00185", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-362", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L362", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00186", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8741", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1509", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_39", "id": "product-blind-v2-00187", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13122", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2251", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00188", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-887", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L887", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00189", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15676", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2683", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00190", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8635", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1493", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00191", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-865", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L865", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00192", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1928028226-comment-5", "sourceURL": "https://github.com/huggingface/datasets/issues/6279", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00193", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1687", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1687", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00194", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-5053962", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/5053962", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00195", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2203", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2203", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00196", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1801", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1801", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00197", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5016", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=869", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_9", "id": "product-blind-v2-00198", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10177", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1770", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00199", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-757", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L757", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_54", "id": "product-blind-v2-00200", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-12558", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2173", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00201", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-28617", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-28617", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00202", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-97", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L97", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00203", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-7199", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1193", "stratumAvailable": 2, "stratumSelected": 2, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00204", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-104", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L104", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_10", "id": "product-blind-v2-00205", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13847", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2373", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00206", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1730299852", "sourceURL": "https://github.com/huggingface/datasets/issues/5912", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_45", "id": "product-blind-v2-00207", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-540", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=109", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00208", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-793", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L793", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00209", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-510", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L510", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00210", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16296", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2683", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00211", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6764", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1197", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00212", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5009", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=866", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00213", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13178", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2262", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00214", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1917", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1917", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00215", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-498", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L498", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00216", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1216", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1216", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00217", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1126", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1126", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00218", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1796083437", "sourceURL": "https://github.com/huggingface/datasets/issues/6013", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00219", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-336", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L336", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_4", "id": "product-blind-v2-00220", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14919", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2559", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00221", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2309", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2309", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00222", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-360", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L360", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00223", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-694", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L694", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00224", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1093", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1093", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00225", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-92", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L92", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00226", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-581", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L581", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00227", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-267", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L267", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00228", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15557", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2662", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00229", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7100", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1253", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00230", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-3708324", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/3708324", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00231", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-2821", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-2821", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00232", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1159", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1159", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00233", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-487", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L487", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00234", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1718", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1718", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00235", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-5373145", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/5373145", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00236", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1990", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1990", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00237", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-5369853", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/5369853", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": null, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_23", "id": "product-blind-v2-00238", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1658", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=280", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00239", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-405", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L405", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00240", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2995780283", "sourceURL": "https://github.com/huggingface/datasets/issues/7516", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00241", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1212", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1212", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00242", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2177", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2177", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_36", "id": "product-blind-v2-00243", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9438", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1633", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_35", "id": "product-blind-v2-00244", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1715", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=290", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00245", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2424488648", "sourceURL": "https://github.com/huggingface/datasets/issues/7063", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00246", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4402", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=766", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00247", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1103", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1103", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00248", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1909", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1909", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_59", "id": "product-blind-v2-00249", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10759", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1875", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00250", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-728", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L728", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00251", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1848914830", "sourceURL": "https://github.com/huggingface/datasets/issues/6147", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00252", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-346", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L346", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00253", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-5150086", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/5150086", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00254", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-2651", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-2651", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00255", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-21108", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-21108", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00256", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-583", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L583", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_20", "id": "product-blind-v2-00257", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9700", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1676", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00258", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4119", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=700", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00259", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-297", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L297", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00260", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-39305", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-39305", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_53", "id": "product-blind-v2-00261", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-10846", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1798", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00262", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2268622609-comment-3", "sourceURL": "https://github.com/huggingface/datasets/issues/6848", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00263", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-2761763", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/2761763", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00264", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1988710061", "sourceURL": "https://github.com/huggingface/datasets/issues/6401", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00265", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-8388", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-8388", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00266", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-5160352", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/5160352", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00267", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2124", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2124", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00268", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1789782693", "sourceURL": "https://github.com/huggingface/datasets/issues/6007", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00269", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6043416", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6043416", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00270", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1100", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1100", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_26", "id": "product-blind-v2-00271", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13799", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2370", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00272", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-17170", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2965", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_16", "id": "product-blind-v2-00273", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-4544", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=740", "stratumAvailable": 4, "stratumSelected": 4, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00274", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-15488", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2538", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_asap_complaint", "id": "product-blind-v2-00275", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-7034", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-7034", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00276", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2466510783", "sourceURL": "https://github.com/huggingface/datasets/issues/7101", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00277", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-3089578", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/3089578", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00278", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-4841850", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/4841850", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00279", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-912", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L912", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00280", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-376", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L376", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00281", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-206", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L206", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00282", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-966", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L966", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00283", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15626", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2672", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_0", "id": "product-blind-v2-00284", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2914", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=487", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00285", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-8004", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1314", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00286", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1280", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1280", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_7", "id": "product-blind-v2-00287", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3103", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=521", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00288", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-654", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L654", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00289", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6144209", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6144209", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00290", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-151", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L151", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00291", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1081", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1081", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00292", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1056", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1056", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_45", "id": "product-blind-v2-00293", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11335", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1977", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00294", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1193", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1193", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00295", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-16317", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2798", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00296", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1781", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1781", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00297", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1617", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1617", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00298", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-431", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L431", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00299", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4319", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=752", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00300", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2911202445", "sourceURL": "https://github.com/huggingface/datasets/issues/7444", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_15", "id": "product-blind-v2-00301", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16781", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2773", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_9", "id": "product-blind-v2-00302", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10076", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1750", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00303", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-983", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L983", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_4", "id": "product-blind-v2-00304", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13858", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2377", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00305", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2326", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2326", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00306", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-488", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L488", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00307", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-721", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L721", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00308", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1096", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1096", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00309", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-822", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L822", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00310", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-866", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L866", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00311", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-17151", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2845", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00312", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2063157187", "sourceURL": "https://github.com/huggingface/datasets/issues/6552", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00313", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5301", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=922", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00314", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-837", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=142", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00315", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2167", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=359", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00316", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-16730", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2876", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00317", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-298", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L298", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00318", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1719402643", "sourceURL": "https://github.com/huggingface/datasets/issues/5881", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00319", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-725", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L725", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00320", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-731", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L731", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00321", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-14", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L14", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00322", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-74", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L74", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00323", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15736", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2695", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00324", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-239", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L239", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00325", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1545", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1545", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00326", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-586", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L586", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00327", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-374", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L374", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00328", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3005242422", "sourceURL": "https://github.com/huggingface/datasets/issues/7527", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00329", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-236", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L236", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00330", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6897", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1214", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00331", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1705", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1705", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00332", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-72", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L72", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00333", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1780", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1780", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00334", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3276677990", "sourceURL": "https://github.com/huggingface/datasets/issues/7709", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00335", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-836", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L836", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00336", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4930", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=848", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00337", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-14838", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2439", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_36", "id": "product-blind-v2-00338", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9225", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1596", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00339", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14605", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2512", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00340", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-36263", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-36263", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00341", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14787", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2540", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00342", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-428", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L428", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": true, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00343", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6842663", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6842663", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00344", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-767", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=138", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00345", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-16294", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-16294", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00346", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2056002548", "sourceURL": "https://github.com/huggingface/datasets/issues/6534", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00347", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16791", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2774", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00348", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6836", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1206", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_40", "id": "product-blind-v2-00349", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3386", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=568", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00350", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2475004644", "sourceURL": "https://github.com/huggingface/datasets/issues/7112", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00351", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2815649092-comment-2", "sourceURL": "https://github.com/huggingface/datasets/issues/7381", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00352", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1964", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1964", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_6", "id": "product-blind-v2-00353", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11844", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2067", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00354", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-528", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L528", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00355", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "blessing", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3253433350-comment-2", "sourceURL": "https://github.com/huggingface/datasets/issues/7696", "stratumAvailable": 3, "stratumSelected": 3, "weakSourceLabels": {"blessing": true, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_3", "id": "product-blind-v2-00356", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3276", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=550", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00357", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1871582175", "sourceURL": "https://github.com/huggingface/datasets/issues/6190", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00358", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-268", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L268", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00359", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-824", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L824", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00360", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-244", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L244", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00361", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-677", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L677", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_18", "id": "product-blind-v2-00362", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1072", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=186", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00363", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1719", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=291", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00364", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-549", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L549", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00365", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14308", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2452", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00366", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-28245", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-28245", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00367", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "blessing", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1963483324-comment-2", "sourceURL": "https://github.com/huggingface/datasets/issues/6354", "stratumAvailable": 3, "stratumSelected": 3, "weakSourceLabels": {"blessing": true, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00368", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1218", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1218", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00369", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-17116", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2951", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00370", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1717", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1717", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00371", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1136", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1136", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00372", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2388064650", "sourceURL": "https://github.com/huggingface/datasets/issues/7022", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00373", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-16593", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2846", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_asap_complaint", "id": "product-blind-v2-00374", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-14991", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-14991", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00375", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2163250590-comment-4", "sourceURL": "https://github.com/huggingface/datasets/issues/6703", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00376", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-359", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L359", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00377", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-318", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L318", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00378", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5043", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=876", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00379", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2148", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2148", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00380", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1711", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1711", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00381", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1169", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1169", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00382", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-3784", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-3784", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00383", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-699", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L699", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00384", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-113", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L113", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00385", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-266", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L266", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00386", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2284839687", "sourceURL": "https://github.com/huggingface/datasets/issues/6884", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00387", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-9401", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-9401", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00388", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-7073", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1171", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00389", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5127", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=888", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00390", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-22771", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-22771", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00391", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1543", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1543", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00392", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-10803", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-10803", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00393", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8967", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1547", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00394", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-388", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L388", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_0", "id": "product-blind-v2-00395", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3995", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=678", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00396", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-187", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L187", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00397", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1621", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1621", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00398", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-3698155", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/3698155", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00399", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1607", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1607", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00400", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1548", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1548", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00401", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14794", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2543", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_26", "id": "product-blind-v2-00402", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14498", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2491", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00403", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-7712", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1263", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_25", "id": "product-blind-v2-00404", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4216", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=725", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00405", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-24309", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-24309", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00406", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1910", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1910", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00407", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1321", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1321", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00408", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-32385", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-32385", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00409", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2876281928", "sourceURL": "https://github.com/huggingface/datasets/issues/7420", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00410", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1978189389", "sourceURL": "https://github.com/huggingface/datasets/issues/6383", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00411", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-2742619", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/2742619", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": null, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00412", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2569837015", "sourceURL": "https://github.com/huggingface/datasets/issues/7201", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00413", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8731", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1507", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00414", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-317", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L317", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00415", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2321", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2321", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00416", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-10473", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-10473", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_8", "id": "product-blind-v2-00417", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5856", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1010", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00418", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-13341", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2178", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00419", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-307", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L307", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00420", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-221", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L221", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00421", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-494", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L494", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_32", "id": "product-blind-v2-00422", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7889", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1367", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00423", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3600", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=614", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00424", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-117", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L117", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_59", "id": "product-blind-v2-00425", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10954", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1913", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00426", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6720", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1185", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00427", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7520", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1308", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_42", "id": "product-blind-v2-00428", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-12851", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2213", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_23", "id": "product-blind-v2-00429", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1862", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=317", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_21", "id": "product-blind-v2-00430", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14549", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2501", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00431", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2314", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2314", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00432", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-524", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L524", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00433", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-994", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L994", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00434", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1132", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1132", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00435", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1850740456", "sourceURL": "https://github.com/huggingface/datasets/issues/6150", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00436", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16559", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2726", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00437", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-15610", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2559", "stratumAvailable": 2, "stratumSelected": 2, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00438", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1990358743", "sourceURL": "https://github.com/huggingface/datasets/issues/6405", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00439", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-17087", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2942", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_17", "id": "product-blind-v2-00440", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15982", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2735", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00441", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-11743", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-11743", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00442", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6901", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1215", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00443", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-171", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L171", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00444", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-296", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L296", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00445", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-16356", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2803", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00446", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-35966", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-35966", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00447", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1220", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1220", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00448", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-437", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L437", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00449", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-580", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L580", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00450", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-7703820", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/7703820", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_30", "id": "product-blind-v2-00451", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6761", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1196", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00452", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-321", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L321", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00453", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-328", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L328", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00454", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-17043", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2819", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00455", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1722", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1722", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00456", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2148609859", "sourceURL": "https://github.com/huggingface/datasets/issues/6688", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_0", "id": "product-blind-v2-00457", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3441", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=582", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_59", "id": "product-blind-v2-00458", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10776", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1879", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00459", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2364", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2364", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00460", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2174398227", "sourceURL": "https://github.com/huggingface/datasets/issues/6724", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_42", "id": "product-blind-v2-00461", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-12604", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2176", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00462", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-25881", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-25881", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_45", "id": "product-blind-v2-00463", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3546", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=600", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00464", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-401", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-401", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00465", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-747", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L747", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00466", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1755197946-comment-5", "sourceURL": "https://github.com/huggingface/datasets/issues/5950", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00467", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-161", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L161", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_39", "id": "product-blind-v2-00468", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-14026", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2298", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00469", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-4629962", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/4629962", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00470", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2341", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2341", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00471", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2035141884", "sourceURL": "https://github.com/huggingface/datasets/issues/6485", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00472", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8035", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1398", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_24", "id": "product-blind-v2-00473", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-426", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=85", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00474", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5837", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1008", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00475", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-681", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L681", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_32", "id": "product-blind-v2-00476", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7777", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1352", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00477", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1547", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=259", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00478", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1221", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1221", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00479", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2499484041", "sourceURL": "https://github.com/huggingface/datasets/issues/7134", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00480", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-85", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L85", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00481", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1161", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1161", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_45", "id": "product-blind-v2-00482", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3717", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=633", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00483", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-738", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=133", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00484", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2320531015", "sourceURL": "https://github.com/huggingface/datasets/issues/6924", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00485", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1304", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1304", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00486", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15732", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2694", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00487", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-598", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L598", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00488", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2176", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2176", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00489", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6936", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1222", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00490", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1742", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1742", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00491", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-827", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L827", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00492", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14412", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2472", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00493", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-397", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L397", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00494", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2423786881", "sourceURL": "https://github.com/huggingface/datasets/issues/7061", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00495", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-103", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L103", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_16", "id": "product-blind-v2-00496", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-89", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=18", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00497", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2447383940", "sourceURL": "https://github.com/huggingface/datasets/issues/7088", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00498", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2371", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2371", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00499", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1774389854", "sourceURL": "https://github.com/huggingface/datasets/issues/5990", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00500", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3238760301", "sourceURL": "https://github.com/huggingface/datasets/issues/7687", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00501", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-908", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L908", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00502", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-82", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L82", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_40", "id": "product-blind-v2-00503", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3570", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=606", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00504", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1317", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1317", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_2", "id": "product-blind-v2-00505", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-12339", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2141", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_30", "id": "product-blind-v2-00506", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8771", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1515", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00507", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2135480811", "sourceURL": "https://github.com/huggingface/datasets/issues/6663", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00508", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5919", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1018", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00509", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-572", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L572", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00510", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-18793", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-18793", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_42", "id": "product-blind-v2-00511", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-12797", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2200", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00512", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3614", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=618", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00513", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2431706568-comment-8", "sourceURL": "https://github.com/huggingface/datasets/issues/7073", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00514", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-260", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L260", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00515", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-0", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=0", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_22", "id": "product-blind-v2-00516", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5370", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=937", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00517", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-93", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L93", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00518", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-589", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L589", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_6", "id": "product-blind-v2-00519", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-11650", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1936", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_0", "id": "product-blind-v2-00520", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3091", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=516", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00521", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1877491602", "sourceURL": "https://github.com/huggingface/datasets/issues/6203", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00522", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6815", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1204", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00523", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1135", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1135", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00524", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1874", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1874", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00525", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1171", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1171", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00526", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-973", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L973", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_4", "id": "product-blind-v2-00527", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13754", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2360", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00528", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-17042", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2818", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00529", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2997422044", "sourceURL": "https://github.com/huggingface/datasets/issues/7520", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00530", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-21", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L21", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00531", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-4011394", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/4011394", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_asap_complaint", "id": "product-blind-v2-00532", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-18288", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-18288", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00533", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-131", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L131", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00534", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-64", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L64", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00535", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1096", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1096", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00536", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3500741658", "sourceURL": "https://github.com/huggingface/datasets/issues/7811", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00537", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1822501472", "sourceURL": "https://github.com/huggingface/datasets/issues/6078", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00538", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-949", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L949", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_56", "id": "product-blind-v2-00539", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4244", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=733", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00540", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2242", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2242", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_20", "id": "product-blind-v2-00541", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9772", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1690", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00542", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16245", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2673", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00543", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2259", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2259", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_40", "id": "product-blind-v2-00544", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-6074", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1052", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00545", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2261078104", "sourceURL": "https://github.com/huggingface/datasets/issues/6834", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00546", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1970140392", "sourceURL": "https://github.com/huggingface/datasets/issues/6365", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00547", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4601", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=796", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00548", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-44929", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-44929", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00549", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1862360199", "sourceURL": "https://github.com/huggingface/datasets/issues/6169", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00550", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-7711", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1262", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00551", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7449", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1296", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_36", "id": "product-blind-v2-00552", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9426", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1632", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00553", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1768271343-comment-3", "sourceURL": "https://github.com/huggingface/datasets/issues/5975", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00554", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1070", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1070", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00555", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1929551712-comment-1", "sourceURL": "https://github.com/huggingface/datasets/issues/6284", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00556", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-153", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L153", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00557", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-530", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L530", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_asap_complaint", "id": "product-blind-v2-00558", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-38413", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-38413", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00559", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1947", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1947", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00560", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2348", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2348", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_32", "id": "product-blind-v2-00561", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-7524", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1231", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00562", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2045", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2045", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00563", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2150800065", "sourceURL": "https://github.com/huggingface/datasets/issues/6690", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_6", "id": "product-blind-v2-00564", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11999", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2094", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00565", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-952", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L952", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00566", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-823", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L823", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00567", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2278", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2278", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00568", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-500", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L500", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00569", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16459", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2713", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_2", "id": "product-blind-v2-00570", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-12689", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2080", "stratumAvailable": 4, "stratumSelected": 4, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00571", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-538", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L538", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_20", "id": "product-blind-v2-00572", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9812", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1693", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00573", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3216857559", "sourceURL": "https://github.com/huggingface/datasets/issues/7676", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_54", "id": "product-blind-v2-00574", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-12608", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2178", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00575", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1544", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1544", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00576", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-13340", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2177", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00577", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-537", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L537", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_18", "id": "product-blind-v2-00578", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-5574", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=968", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_43", "id": "product-blind-v2-00579", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-3114", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=493", "stratumAvailable": 4, "stratumSelected": 4, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_58", "id": "product-blind-v2-00580", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11331", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1976", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_59", "id": "product-blind-v2-00581", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10760", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1876", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00582", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-28345", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-28345", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": null, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00583", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2868701471", "sourceURL": "https://github.com/huggingface/datasets/issues/7418", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_26", "id": "product-blind-v2-00584", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14700", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2528", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00585", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-314", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L314", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00586", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-73", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L73", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_35", "id": "product-blind-v2-00587", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1639", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=275", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00588", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-933", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L933", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00589", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-7377432", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/7377432", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00590", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-706", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L706", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00591", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6884170", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6884170", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00592", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2069", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2069", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00593", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-3058", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-3058", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00594", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-43141", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-43141", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00595", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-515", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L515", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00596", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7557", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1316", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_32", "id": "product-blind-v2-00597", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-8496", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1475", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00598", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1158", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1158", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00599", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-7262967", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/7262967", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00600", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-969", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L969", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00601", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-75", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L75", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00602", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-13342", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2179", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00603", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-347", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L347", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00604", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7563", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1318", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_1", "id": "product-blind-v2-00605", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-1511", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=251", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00606", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1138", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1138", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00607", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-391", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L391", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00608", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1125", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1125", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00609", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-658", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L658", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00610", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3398", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=570", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00611", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1844", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1844", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": true, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00612", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-38847", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-38847", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00613", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-886", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L886", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00614", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7556", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1315", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00615", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "blessing", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-471", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L471", "stratumAvailable": 3, "stratumSelected": 3, "weakSourceLabels": {"blessing": true, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00616", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-7598", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1246", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00617", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-67", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L67", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_15", "id": "product-blind-v2-00618", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16694", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2751", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00619", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1123", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1123", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00620", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16072", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2644", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00621", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2679", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=449", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00622", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-653", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L653", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00623", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-313", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L313", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_0", "id": "product-blind-v2-00624", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-686", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=128", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00625", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2302", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2302", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00626", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-893", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L893", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00627", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14770", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2539", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00628", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1099", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1099", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00629", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1804183858", "sourceURL": "https://github.com/huggingface/datasets/issues/6031", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00630", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-503", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L503", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00631", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1021", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1021", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00632", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-21114", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-21114", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00633", "inclusionProbability": 1.0, "language": "en", "samplingStratum": "confirmationDecision", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-708", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L708", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": true, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00634", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1335", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1335", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00635", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1177", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1177", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00636", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-19559", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-19559", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00637", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1527", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1527", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00638", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-531", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L531", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00639", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2311", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2311", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_36", "id": "product-blind-v2-00640", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9640", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1665", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00641", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2922676278-comment-6", "sourceURL": "https://github.com/huggingface/datasets/issues/7456", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00642", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1804358679", "sourceURL": "https://github.com/huggingface/datasets/issues/6032", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00643", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-3168283589", "sourceURL": "https://github.com/huggingface/datasets/issues/7632", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00644", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-4104", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=697", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00645", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2211", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2211", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00646", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-22258", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-22258", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00647", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-335", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L335", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00648", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1743922028", "sourceURL": "https://github.com/huggingface/datasets/issues/5926", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00649", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-325", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L325", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00650", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-218", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L218", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00651", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-548", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L548", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00652", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2491942650", "sourceURL": "https://github.com/huggingface/datasets/issues/7129", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00653", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-259", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L259", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00654", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-2664467", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/2664467", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00655", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-527", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L527", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00656", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7916", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1375", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_58", "id": "product-blind-v2-00657", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11366", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1986", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00658", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2372", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2372", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00659", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1078", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1078", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00660", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14917", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2558", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_12", "id": "product-blind-v2-00661", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-13467", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2309", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00662", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2235768891", "sourceURL": "https://github.com/huggingface/datasets/issues/6798", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00663", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-49", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L49", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00664", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-504", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L504", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00665", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1763648540", "sourceURL": "https://github.com/huggingface/datasets/issues/5965", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00666", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-736", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L736", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00667", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-872", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L872", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00668", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1662", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1662", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_53", "id": "product-blind-v2-00669", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10525", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1836", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_58", "id": "product-blind-v2-00670", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11328", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1975", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00671", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-1746557", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/1746557", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00672", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-7718", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1264", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_asap_complaint", "id": "product-blind-v2-00673", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-37349", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-37349", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00674", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2287", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2287", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00675", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-1107", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L1107", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_13", "id": "product-blind-v2-00676", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3784", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=648", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_49", "id": "product-blind-v2-00677", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14306", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2451", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_23", "id": "product-blind-v2-00678", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-3162", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=532", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_39", "id": "product-blind-v2-00679", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-13312", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2174", "stratumAvailable": 12, "stratumSelected": 12, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00680", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-491", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L491", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00681", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-10606", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-10606", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00682", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-871", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L871", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00683", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1737", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1737", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00684", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2264", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2264", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_47", "id": "product-blind-v2-00685", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15610", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2670", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00686", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-146", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L146", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00687", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1378", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1378", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_21", "id": "product-blind-v2-00688", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-10636", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1852", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_comment_intent", "id": "product-blind-v2-00689", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1972073909-comment-1", "sourceURL": "https://github.com/huggingface/datasets/issues/6370", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00690", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-16883", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2902", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_massive_intent_58", "id": "product-blind-v2-00691", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-11554", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2022", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00692", "inclusionProbability": 0.05841121495327103, "language": "en", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-9124", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1578", "stratumAvailable": 856, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00693", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2228081955", "sourceURL": "https://github.com/huggingface/datasets/issues/6782", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00694", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-435", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L435", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00695", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16082", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2646", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_github_issue_title", "id": "product-blind-v2-00696", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-2279385159", "sourceURL": "https://github.com/huggingface/datasets/issues/6868", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_4", "id": "product-blind-v2-00697", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-14926", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2561", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_github_issue_title", "id": "product-blind-v2-00698", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "Sulak2020 GitHub issues multi-repo dataset", "sourceLicense": "CC-BY-4.0 dataset / attributed source issue", "sourceRecordID": "comprehensive-github-1961268504", "sourceURL": "https://github.com/huggingface/datasets/issues/6348", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_44", "id": "product-blind-v2-00699", "inclusionProbability": 0.0801068090787717, "language": "en", "samplingStratum": "question", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-15970", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2733", "stratumAvailable": 1498, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00700", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1442", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1442", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00701", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-6819", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1128", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00702", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-6704114", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/6704114", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00703", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-15045", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-15045", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": true, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00704", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-4632621", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/4632621", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00705", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-934", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L934", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00706", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-2310599", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/2310599", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": null, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00707", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-410", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L410", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_cfpb_complaint", "id": "product-blind-v2-00708", "inclusionProbability": 0.111358574610245, "language": "en", "samplingStratum": "complaint", "sourceDataset": "CFPB via hpe-ai/customer-complaints", "sourceLicense": "CC0-1.0 source / Apache-2.0 mirror", "sourceRecordID": "online-cfpb-2346118", "sourceURL": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/2346118", "stratumAvailable": 449, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00709", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-685", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L685", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00710", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-1819", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L1819", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00711", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-2094", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L2094", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_33", "id": "product-blind-v2-00712", "inclusionProbability": 1.0, "language": "zh-Hans", "samplingStratum": "task", "sourceDataset": "AmazonScience/MASSIVE zh-CN test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-zh-CN-16005", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2630", "stratumAvailable": 28, "stratumSelected": 28, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": true}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00713", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-896", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L896", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": true, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00714", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-395", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L395", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_48", "id": "product-blind-v2-00715", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-2166", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=358", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_pos", "id": "product-blind-v2-00716", "inclusionProbability": 0.746268656716418, "language": "en", "samplingStratum": "scheduleNegotiation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_pos-102", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_pos#L102", "stratumAvailable": 67, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": true, "task": false}} {"family": "online_massive_intent_2", "id": "product-blind-v2-00717", "inclusionProbability": 0.07393715341959335, "language": "en", "samplingStratum": "replyableOnly", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-12536", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=2169", "stratumAvailable": 1623, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00718", "inclusionProbability": 0.05711565920990005, "language": "en", "samplingStratum": "noWeakIntent", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-875", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L875", "stratumAvailable": 2101, "stratumSelected": 120, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_massive_intent_50", "id": "product-blind-v2-00719", "inclusionProbability": 0.45871559633027525, "language": "en", "samplingStratum": "followUpReminder", "sourceDataset": "AmazonScience/MASSIVE en-US test", "sourceLicense": "CC-BY-4.0", "sourceRecordID": "comprehensive-massive-en-US-7542", "sourceURL": "https://huggingface.co/datasets/AmazonScience/massive?row=1313", "stratumAvailable": 109, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": true, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}} {"family": "online_enron_intent_neg", "id": "product-blind-v2-00720", "inclusionProbability": 0.9433962264150944, "language": "en", "samplingStratum": "invitation", "sourceDataset": "Verified Enron Intent Dataset", "sourceLicense": "MIT / public Enron source corpus", "sourceRecordID": "comprehensive-enron-intent_neg-48", "sourceURL": "https://github.com/vseledkin/enron_intent_dataset_verified/blob/master/intent_neg#L48", "stratumAvailable": 53, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": false, "confirmationDecision": false, "followUpReminder": false, "invitation": true, "question": false, "replyable": false, "scheduleNegotiation": false, "task": false}} {"family": "online_asap_complaint", "id": "product-blind-v2-00721", "inclusionProbability": 0.4098360655737705, "language": "zh-Hans", "samplingStratum": "complaint", "sourceDataset": "Meituan-Dianping/ASAP test", "sourceLicense": "Apache-2.0", "sourceRecordID": "online-asap-30958", "sourceURL": "https://github.com/Meituan-Dianping/asap/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/test.csv#row-30958", "stratumAvailable": 122, "stratumSelected": 50, "weakSourceLabels": {"blessing": false, "complaint": true, "confirmationDecision": false, "followUpReminder": false, "invitation": false, "question": false, "replyable": true, "scheduleNegotiation": false, "task": false}}