2601.06193v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.670000Z",
      "hash": "1debc8e3632e987d5519ed9f37d70c5354d9790c4e97c48357d488f49fb9a347",
      "id": "11e45ccf-b086-4246-9a85-30263efbb354",
      "source": {
        "execution_id": "4a9f9d5f-bdb3-4043-8ccd-18fbeab62da1",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "1debc8e3632e987d5519ed9f37d70c5354d9790c4e97c48357d488f49fb9a347",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06193v1.pdf",
      "size": 4470686
    },
    "source": {
      "execution_id": "bec96236-e7f0-4477-b4fc-2a0a8a21bd1a",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "creation_date": "2026-01-13T01:07:53Z",
      "keywords": [
        "Large Language Models",
        "Benchmark",
        "Medical AI",
        "Healthcare",
        "Evaluation",
        "Supervised Fine-Tuning"
      ],
      "modified_date": "2026-01-13T01:07:53Z",
      "page_count": 11,
      "producer": "pikepdf 8.15.1",
      "subject": "-  Computing methodologies  -\u003e  Natural language generation.-  Applied computing  -\u003e  Health care information systems.",
      "title": "MLB: A Scenario-Driven Benchmark for Evaluating Large Language Models in Clinical Applications",
      "version": "1.7"
    },
    "source": {
      "execution_id": "9d4ff372-033c-4bca-a3f6-0ad6d223c0a2",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}