2601.08134v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:15.373000Z",
      "hash": "d25afbb77a03115d1c6bb9d1b8fb26097b33a896985f158d0539307d816f075b",
      "id": "722ca020-eb88-4461-bc61-2aa31c0bc366",
      "source": {
        "execution_id": "8d41135f-8765-4404-b5e2-d55e2e18884a",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "d25afbb77a03115d1c6bb9d1b8fb26097b33a896985f158d0539307d816f075b",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.08134v1.pdf",
      "size": 3169426
    },
    "source": {
      "execution_id": "895d8dfe-a42f-4817-a503-7814727c46a2",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 86,
      "producer": "pikepdf 8.15.1",
      "title": "How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains",
      "version": "1.7"
    },
    "source": {
      "execution_id": "7dcf4583-a3da-4039-89b8-2f80fb0a9d6f",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}