provenance.json

{
  "passed": true,
  "checked_at_utc": "2026-09-27T02:40:28.055408+00:00",
  "scope": "DuDE training data; upstream Qwen pretraining coverage is not known",
  "examples": [
    {
      "label": "Sample 1",
      "conversation_id": "V01_S0192_I00000307",
      "example_id": "V01_S0192_I00000307-0000",
      "split": "dev",
      "participants": {
        "A": "V01_P1356",
        "B": "V01_P1357"
      },
      "transcript_source": "own_Qwen3-ASR+ForcedAligner+PANNs",
      "dataset_transcript_downloaded": false,
      "annotation_sha256": "76474198f55a6d7afd7f826cd910b9841af8293a32413f2f8b672c1ef7fd4996",
      "public_example_id": "sample_1"
    },
    {
      "label": "Sample 2",
      "conversation_id": "V01_S0220_I00000126",
      "example_id": "V01_S0220_I00000126-0000",
      "split": "dev",
      "participants": {
        "A": "V01_P1409",
        "B": "V01_P1500"
      },
      "transcript_source": "own_Qwen3-ASR+ForcedAligner+PANNs",
      "dataset_transcript_downloaded": false,
      "annotation_sha256": "d3d434ee2d09aa3916f1883df7e1b1134125b285a2a09cac64171c49110d1cb6",
      "public_example_id": "sample_2"
    }
  ],
  "training_manifests": [
    {
      "corpus": "seamless-100h",
      "train_conversations": 1468,
      "sha256": "05c7e77c69078b9d68ef3c30a68392d893f82f7a5cca94bdbf2e3a4ced40d282",
      "conversation_matches": [],
      "participant_matches": [],
      "featured_conversations_in_dev": [
        "V01_S0220_I00000126"
      ]
    },
    {
      "corpus": "seamless-500h-v1",
      "train_conversations": 7365,
      "sha256": "2967b0c49574182fd14d56571107dbc264f199d6cd3ed39ea71bc9956a81203a",
      "conversation_matches": [],
      "participant_matches": [],
      "featured_conversations_in_dev": [
        "V01_S0192_I00000307",
        "V01_S0220_I00000126"
      ]
    },
    {
      "corpus": "seamless-2000h-v1",
      "train_conversations": 31493,
      "sha256": "08d437e07c00ebd4a73feed219e0048e69d1bdcb681dac12f20b0fd9c803758e",
      "conversation_matches": [],
      "participant_matches": [],
      "featured_conversations_in_dev": [
        "V01_S0192_I00000307",
        "V01_S0220_I00000126"
      ]
    }
  ],
  "training_codec_caches": [
    {
      "corpus": "conversation-2000h-v1",
      "shards": 8,
      "examples": 30854,
      "featured_conversation_matches": []
    },
    {
      "corpus": "conversation-500h-full-v1",
      "shards": 4,
      "examples": 7190,
      "featured_conversation_matches": []
    }
  ],
  "transcript_note": "XML uses our ASR/event annotations of held-out Seamless Interaction audio, not dataset-provided transcripts.",
  "voice_reference_note": "Speaker reference clips are provided during inference; they are not training examples."
}