2601.06896v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.653000Z",
      "hash": "900fd7083e309c658b2692f3f79c5668ebf773def115f68c100cac6324635f3f",
      "id": "808d09ee-039c-4371-9d2c-66621821dc4c",
      "source": {
        "execution_id": "38ec8013-172c-4ef3-b181-a47263c69709",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "900fd7083e309c658b2692f3f79c5668ebf773def115f68c100cac6324635f3f",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06896v1.pdf",
      "size": 892178
    },
    "source": {
      "execution_id": "8b8ff233-17b2-4664-b5c5-f9f7efd54661",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 15,
      "producer": "pikepdf 8.15.1",
      "title": "TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding",
      "version": "1.7"
    },
    "source": {
      "execution_id": "13cb3f1e-52bc-4221-9943-5afb8a26dfe4",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}