2601.10306v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:23.626000Z",
      "hash": "d15c334f30617aa233456bac4872d8671621bd8d50cc361bcbafeebac3115ad3",
      "id": "54d7bea6-6b95-4c2a-80aa-00d1ff7d782c",
      "source": {
        "execution_id": "a43803ea-351e-425e-9af7-67d196c8b975",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "d15c334f30617aa233456bac4872d8671621bd8d50cc361bcbafeebac3115ad3",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.10306v1.pdf",
      "size": 1089258
    },
    "source": {
      "execution_id": "8ac1de90-f4d1-43cf-bdf0-f43d27b600e7",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 14,
      "producer": "pikepdf 8.15.1",
      "title": "Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "5b58eae6-7f75-4fd7-8c69-4ea2a17d0fa1",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}