{
  "baseCorpusRecords": 17692,
  "combinedCorpusSHA256": "f111bc7425912213082e01038b52dd3d25fe21418d156f532da8f01f27fa16e4",
  "combinedRecords": 21537,
  "excludedBaseOverlap": 6,
  "excludedHoldoutOverlap": 72,
  "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": 3845,
  "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",
      "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": 798
      },
      "languages": {
        "en": 1198
      },
      "license": "Apache-2.0",
      "records": 1198,
      "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": 27,
        "question": 83,
        "task": 222
      },
      "languages": {
        "en": 465
      },
      "license": "CDLA-Permissive-1.0",
      "records": 465,
      "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"
    }
  ],
  "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)>"
    }
  ]
}