2601.08134v2.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:15.942000Z",
      "hash": "3036a26d49521cdb97c097dcbd3be3d25ef9170e6bcbc944888b9acbd4ceec08",
      "id": "4250f48a-06a0-4a8d-85a5-4dc76ab33387",
      "source": {
        "execution_id": "810676a2-dc28-452b-8202-e23cc4225c9b",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "3036a26d49521cdb97c097dcbd3be3d25ef9170e6bcbc944888b9acbd4ceec08",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.08134v2.pdf",
      "size": 3170305
    },
    "source": {
      "execution_id": "9d09face-63bf-470f-ba1a-8f0a40039441",
      "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": "772508a3-afec-4cbd-b2d3-810b114be06c",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}