docs(ai): record AI and clipboard semantics updates
- Document the smart reply center, clipboard semantic v6 specialization, personal style generation fix, and durable Apple account session work in both English and Simplified Chinese. - Update clipboard semantics README and open-training sources to reflect the v6 boundary, blessing, and consensus-adjudication corpora that the new release-gate pipeline consumes.
This commit is contained in:
Rocky
@@ -1,9 +1,9 @@
|
||||
{
|
||||
"baseCorpusRecords": 17692,
|
||||
"combinedCorpusSHA256": "f111bc7425912213082e01038b52dd3d25fe21418d156f532da8f01f27fa16e4",
|
||||
"combinedRecords": 21537,
|
||||
"combinedCorpusSHA256": "24bbec3fb9b3cc6434582d660b03b37401abe1339185405115646675ec3b654a",
|
||||
"combinedRecords": 48779,
|
||||
"excludedBaseOverlap": 6,
|
||||
"excludedHoldoutOverlap": 72,
|
||||
"excludedHoldoutOverlap": 425,
|
||||
"excludedSources": [
|
||||
{
|
||||
"dataset": "MIDAS",
|
||||
@@ -36,60 +36,136 @@
|
||||
{
|
||||
"dataset": "Verified Enron Intent / GitHub issue holdout source",
|
||||
"reason": "No clean official train split independent from the frozen holdout."
|
||||
},
|
||||
{
|
||||
"dataset": "CFPB",
|
||||
"reason": "No official train split; the source is already represented in frozen evaluation data and contains privacy-sensitive narratives."
|
||||
},
|
||||
{
|
||||
"dataset": "CLINC150",
|
||||
"reason": "Kept isolated from product training because its assistant intents are not aligned with the product-policy taxonomy."
|
||||
},
|
||||
{
|
||||
"dataset": "openclaw-zh-greetings / WeChat-AutoSendBless",
|
||||
"reason": "Repository licenses do not establish a sufficiently clear, versioned rights chain for the underlying message templates."
|
||||
}
|
||||
],
|
||||
"openTrainingRecords": 3845,
|
||||
"openTrainingRecords": 31087,
|
||||
"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": "CrossWOZ",
|
||||
"dataset": "AmazonScience/MASSIVE en-US",
|
||||
"knownLabelCounts": {
|
||||
"question": 279,
|
||||
"task": 258
|
||||
"assistantCommand": 3658,
|
||||
"domain": 9824,
|
||||
"informationQuery": 5307,
|
||||
"sentiment": 126,
|
||||
"task": 358
|
||||
},
|
||||
"languages": {
|
||||
"zh-Hans": 544
|
||||
"en": 10810
|
||||
},
|
||||
"license": "CC-BY-4.0",
|
||||
"records": 10810,
|
||||
"revision": "1.1",
|
||||
"url": "https://huggingface.co/datasets/AmazonScience/massive"
|
||||
},
|
||||
{
|
||||
"dataset": "AmazonScience/MASSIVE zh-CN",
|
||||
"knownLabelCounts": {
|
||||
"assistantCommand": 3272,
|
||||
"domain": 9166,
|
||||
"informationQuery": 5025,
|
||||
"sentiment": 120,
|
||||
"task": 348
|
||||
},
|
||||
"languages": {
|
||||
"zh-Hans": 10099
|
||||
},
|
||||
"license": "CC-BY-4.0",
|
||||
"records": 10099,
|
||||
"revision": "1.1",
|
||||
"url": "https://huggingface.co/datasets/AmazonScience/massive"
|
||||
},
|
||||
{
|
||||
"dataset": "CrossWOZ",
|
||||
"knownLabelCounts": {
|
||||
"domain": 476,
|
||||
"informationQuery": 393
|
||||
},
|
||||
"languages": {
|
||||
"zh-Hans": 599
|
||||
},
|
||||
"license": "Apache-2.0",
|
||||
"records": 544,
|
||||
"records": 599,
|
||||
"revision": "df82c9fdff91b9b130f2d6b89110d3870ba6260e",
|
||||
"url": "https://github.com/thu-coai/CrossWOZ/blob/df82c9fdff91b9b130f2d6b89110d3870ba6260e/data/crosswoz/train.json.zip"
|
||||
},
|
||||
{
|
||||
"dataset": "Google Research GoEmotions",
|
||||
"dataset": "FormosaNLU Synth v1",
|
||||
"knownLabelCounts": {
|
||||
"sentiment": 798
|
||||
"assistantCommand": 839,
|
||||
"domain": 1747,
|
||||
"informationQuery": 817,
|
||||
"task": 119
|
||||
},
|
||||
"languages": {
|
||||
"en": 1198
|
||||
"zh-Hans": 1988
|
||||
},
|
||||
"license": "CC-BY-4.0",
|
||||
"records": 1988,
|
||||
"revision": "03a337b61a200ab690994dca4dc31aa7f209800e",
|
||||
"url": "https://huggingface.co/datasets/steven0226/formosa-nlu-synth-v1/resolve/03a337b61a200ab690994dca4dc31aa7f209800e/data/train.jsonl"
|
||||
},
|
||||
{
|
||||
"dataset": "Google Research GoEmotions",
|
||||
"knownLabelCounts": {
|
||||
"sentiment": 799
|
||||
},
|
||||
"languages": {
|
||||
"en": 1199
|
||||
},
|
||||
"license": "Apache-2.0",
|
||||
"records": 1198,
|
||||
"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
|
||||
"domain": 631
|
||||
},
|
||||
"languages": {
|
||||
"en": 638
|
||||
"en": 631
|
||||
},
|
||||
"license": "CC-BY-4.0",
|
||||
"records": 638,
|
||||
"records": 631,
|
||||
"revision": "d92cb6af3005f1dc09c39e75e7daf4a04905e00b",
|
||||
"url": "https://github.com/google-research-datasets/Taskmaster/tree/d92cb6af3005f1dc09c39e75e7daf4a04905e00b/TM-1-2019"
|
||||
},
|
||||
{
|
||||
"dataset": "HLTCHKUST/BiToD",
|
||||
"knownLabelCounts": {
|
||||
"domain": 1339,
|
||||
"informationQuery": 885,
|
||||
"task": 355
|
||||
},
|
||||
"languages": {
|
||||
"en": 681,
|
||||
"zh-Hans": 658
|
||||
},
|
||||
"license": "Apache-2.0",
|
||||
"records": 1339,
|
||||
"revision": "a9bd74de9eecdc3d875cb4ebf6a6beaf9c30c2ff",
|
||||
"url": "https://raw.githubusercontent.com/HLTCHKUST/BiToD/a9bd74de9eecdc3d875cb4ebf6a6beaf9c30c2ff/data/zh_train.json"
|
||||
},
|
||||
{
|
||||
"dataset": "Meituan-Dianping/ASAP",
|
||||
"knownLabelCounts": {
|
||||
"complaint": 500,
|
||||
"domain": 1000,
|
||||
"sentiment": 1000
|
||||
},
|
||||
"languages": {
|
||||
@@ -103,31 +179,62 @@
|
||||
{
|
||||
"dataset": "MultiDoGO",
|
||||
"knownLabelCounts": {
|
||||
"confirmationDecision": 27,
|
||||
"question": 83,
|
||||
"task": 222
|
||||
"domain": 464,
|
||||
"informationQuery": 61,
|
||||
"task": 83
|
||||
},
|
||||
"languages": {
|
||||
"en": 465
|
||||
"en": 464
|
||||
},
|
||||
"license": "CDLA-Permissive-1.0",
|
||||
"records": 465,
|
||||
"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/software/train.tsv"
|
||||
"url": "https://github.com/awslabs/multi-domain-goal-oriented-dialogues-dataset/blob/baa30639c4b271f394b81443c842193407cdf26d/data/paper_splits/splits_annotated_at_turn_level/airline/train.tsv"
|
||||
},
|
||||
{
|
||||
"dataset": "PolyAI MInDS-14 zh-CN",
|
||||
"knownLabelCounts": {
|
||||
"assistantCommand": 163,
|
||||
"domain": 480,
|
||||
"informationQuery": 179
|
||||
},
|
||||
"languages": {
|
||||
"zh-Hans": 480
|
||||
},
|
||||
"license": "CC-BY-4.0",
|
||||
"records": 480,
|
||||
"revision": "40ce77cb32a384e4d50a568e1ec39ac804019d33",
|
||||
"url": "https://huggingface.co/datasets/PolyAI/minds14/resolve/40ce77cb32a384e4d50a568e1ec39ac804019d33/zh-CN/train-00000-of-00001.parquet"
|
||||
},
|
||||
{
|
||||
"dataset": "PolyAI RESTAURANTS-8K",
|
||||
"knownLabelCounts": {
|
||||
"domain": 986
|
||||
},
|
||||
"languages": {
|
||||
"en": 986
|
||||
},
|
||||
"license": "CC-BY-4.0",
|
||||
"records": 986,
|
||||
"revision": "57ec275d8078af65b7731c2a98be812d844a6d6b",
|
||||
"url": "https://raw.githubusercontent.com/PolyAI-LDN/task-specific-datasets/57ec275d8078af65b7731c2a98be812d844a6d6b/span_extraction/restaurant8k/train_0.json"
|
||||
},
|
||||
{
|
||||
"dataset": "SNIPS NLU Benchmark",
|
||||
"knownLabelCounts": {
|
||||
"assistantCommand": 499,
|
||||
"domain": 1492,
|
||||
"informationQuery": 743,
|
||||
"task": 250
|
||||
},
|
||||
"languages": {
|
||||
"en": 1492
|
||||
},
|
||||
"license": "CC0-1.0",
|
||||
"records": 1492,
|
||||
"revision": "b86ac7f1577868c42158d0dec77db50956046696",
|
||||
"url": "https://raw.githubusercontent.com/sonos/nlu-benchmark/b86ac7f1577868c42158d0dec77db50956046696/2017-06-custom-intent-engines/BookRestaurant/train_BookRestaurant_full.json"
|
||||
}
|
||||
],
|
||||
"unavailableSources": [
|
||||
{
|
||||
"dataset": "MASSIVE",
|
||||
"reason": "URLError: <urlopen error [SSL: UNEXPECTED_EOF_WHILE_READING] EOF occurred in violation of protocol (_ssl.c:1000)>"
|
||||
},
|
||||
{
|
||||
"dataset": "CLINC150",
|
||||
"reason": "URLError: <urlopen error [SSL: UNEXPECTED_EOF_WHILE_READING] EOF occurred in violation of protocol (_ssl.c:1000)>"
|
||||
},
|
||||
{
|
||||
"dataset": "CFPB",
|
||||
"reason": "URLError: <urlopen error [SSL: UNEXPECTED_EOF_WHILE_READING] EOF occurred in violation of protocol (_ssl.c:1000)>"
|
||||
}
|
||||
]
|
||||
"unavailableSources": []
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user