Cursor: Apply local changes for cloud agent

2026-08-27 18:01:46 +08:00
parent 39002336c0
commit 42e6252f01
148 changed files with 120105 additions and 8122 deletions
@@ -0,0 +1,180 @@
+{
+  "baseCorpusRecords": 17692,
+  "combinedCorpusSHA256": "70d1547b41b08e4417cfa86ad93dd5637b557d174c6503575c44fbf152cc3ee5",
+  "combinedRecords": 23918,
+  "excludedBaseOverlap": 6,
+  "excludedHoldoutOverlap": 151,
+  "excludedSources": [
+    {
+      "dataset": "MIDAS",
+      "reason": "Upstream deleted da_data in commit 509eb7e78b6661e54883fe3522ba60aaddcf69f2; deleted data is not resurrected for training."
+    },
+    {
+      "dataset": "DailyDialog / EmpatheticDialogues / Switchboard",
+      "reason": "Non-commercial license restriction."
+    },
+    {
+      "dataset": "NormDial / xLLMs Dialogue Greetings",
+      "reason": "No clear standard dataset license."
+    },
+    {
+      "dataset": "Schema-Guided Dialogue",
+      "reason": "CC-BY-SA-4.0 compatibility requires legal review."
+    },
+    {
+      "dataset": "Stanford Politeness Corpus",
+      "reason": "The downloadable archive does not include an explicit corpus license; source comments may carry ShareAlike obligations."
+    },
+    {
+      "dataset": "CPED",
+      "reason": "The Apache repository license does not establish commercial training rights for dialogue transcribed from copyrighted TV shows."
+    },
+    {
+      "dataset": "Tianji Wishes / Birthday Quotes",
+      "reason": "Dataset-level licenses do not provide a sufficiently clear per-record source or synthetic-generation rights chain."
+    },
+    {
+      "dataset": "Verified Enron Intent / GitHub issue holdout source",
+      "reason": "No clean official train split independent from the frozen holdout."
+    }
+  ],
+  "openTrainingRecords": 6226,
+  "policy": "Licensed official training splits only. Per-record knownLabels prevent unannotated intents from becoming false negatives. Exact normalized text overlap with every local *holdout-corpus.jsonl file is excluded.",
+  "schemaVersion": 1,
+  "seed": 20260827,
+  "sources": [
+    {
+      "dataset": "AmazonScience/MASSIVE en-US",
+      "knownLabelCounts": {
+        "followUpReminder": 7,
+        "question": 223,
+        "sentiment": 4,
+        "task": 143
+      },
+      "languages": {
+        "en": 498
+      },
+      "license": "CC-BY-4.0",
+      "records": 498,
+      "revision": "1.1",
+      "url": "https://huggingface.co/datasets/AmazonScience/massive"
+    },
+    {
+      "dataset": "AmazonScience/MASSIVE zh-CN",
+      "knownLabelCounts": {
+        "followUpReminder": 3,
+        "question": 212,
+        "sentiment": 6,
+        "task": 165
+      },
+      "languages": {
+        "zh-Hans": 487
+      },
+      "license": "CC-BY-4.0",
+      "records": 487,
+      "revision": "1.1",
+      "url": "https://huggingface.co/datasets/AmazonScience/massive"
+    },
+    {
+      "dataset": "CFPB via hpe-ai/customer-complaints",
+      "knownLabelCounts": {
+        "complaint": 898,
+        "sentiment": 898
+      },
+      "languages": {
+        "en": 898
+      },
+      "license": "CC0-1.0 source / Apache-2.0 mirror",
+      "records": 898,
+      "revision": "e5fec64e1f0688e47699b9cf8c26fe4ed350123a",
+      "url": "https://www.consumerfinance.gov/data-research/consumer-complaints/search/detail/4696537"
+    },
+    {
+      "dataset": "CLINC150 UCI",
+      "knownLabelCounts": {
+        "followUpReminder": 5,
+        "question": 308,
+        "task": 143
+      },
+      "languages": {
+        "en": 498
+      },
+      "license": "CC-BY-3.0",
+      "records": 498,
+      "revision": "UCI-570-2020-05-07",
+      "url": "https://archive.ics.uci.edu/dataset/570/clinc150"
+    },
+    {
+      "dataset": "CrossWOZ",
+      "knownLabelCounts": {
+        "question": 279,
+        "task": 258
+      },
+      "languages": {
+        "zh-Hans": 544
+      },
+      "license": "Apache-2.0",
+      "records": 544,
+      "revision": "df82c9fdff91b9b130f2d6b89110d3870ba6260e",
+      "url": "https://github.com/thu-coai/CrossWOZ/blob/df82c9fdff91b9b130f2d6b89110d3870ba6260e/data/crosswoz/train.json.zip"
+    },
+    {
+      "dataset": "Google Research GoEmotions",
+      "knownLabelCounts": {
+        "sentiment": 799
+      },
+      "languages": {
+        "en": 1199
+      },
+      "license": "Apache-2.0",
+      "records": 1199,
+      "revision": "5d8f4ac97c873bde3a792ba4628f00bb9103d3e6",
+      "url": "https://github.com/google-research/google-research/blob/5d8f4ac97c873bde3a792ba4628f00bb9103d3e6/goemotions/data/train.tsv"
+    },
+    {
+      "dataset": "Google Taskmaster-1",
+      "knownLabelCounts": {
+        "confirmationDecision": 168,
+        "question": 138,
+        "scheduleNegotiation": 4,
+        "task": 90
+      },
+      "languages": {
+        "en": 638
+      },
+      "license": "CC-BY-4.0",
+      "records": 638,
+      "revision": "d92cb6af3005f1dc09c39e75e7daf4a04905e00b",
+      "url": "https://github.com/google-research-datasets/Taskmaster/tree/d92cb6af3005f1dc09c39e75e7daf4a04905e00b/TM-1-2019"
+    },
+    {
+      "dataset": "Meituan-Dianping/ASAP",
+      "knownLabelCounts": {
+        "complaint": 500,
+        "sentiment": 1000
+      },
+      "languages": {
+        "zh-Hans": 1000
+      },
+      "license": "Apache-2.0",
+      "records": 1000,
+      "revision": "975122a60065240124df62cb4d5dbfd19ed9ef2c",
+      "url": "https://github.com/Meituan-Dianping/ASAP/blob/975122a60065240124df62cb4d5dbfd19ed9ef2c/data/train.csv"
+    },
+    {
+      "dataset": "MultiDoGO",
+      "knownLabelCounts": {
+        "confirmationDecision": 28,
+        "question": 83,
+        "task": 222
+      },
+      "languages": {
+        "en": 464
+      },
+      "license": "CDLA-Permissive-1.0",
+      "records": 464,
+      "revision": "baa30639c4b271f394b81443c842193407cdf26d",
+      "url": "https://github.com/awslabs/multi-domain-goal-oriented-dialogues-dataset/blob/baa30639c4b271f394b81443c842193407cdf26d/data/paper_splits/splits_annotated_at_turn_level/insurance/train.tsv"
+    }
+  ]
+}