2601.08421v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:16.200000Z",
      "hash": "0e1812ac08dd167ef2be70f0af06e9c7f1cb4e064f71a77c06e1b43d13468abd",
      "id": "bf95d691-ca0c-4a87-a17e-5d7e3f8faf94",
      "source": {
        "execution_id": "3ee274e0-a43d-4733-8b07-9c38e2a67161",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "0e1812ac08dd167ef2be70f0af06e9c7f1cb4e064f71a77c06e1b43d13468abd",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.08421v1.pdf",
      "size": 1196513
    },
    "source": {
      "execution_id": "c2e84158-186a-4b6c-b682-63dbf79a1b11",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 46,
      "producer": "pikepdf 8.15.1",
      "title": "Coverage Improvement and Fast Convergence of On-policy Preference Learning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "26f22573-4ac3-4b8b-8da7-a5af1dd9d4a8",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}