2601.07182v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:11.752000Z",
      "hash": "0c12ef422474590b519c5e01f78adaf88bf932a9eabff010b1234c6922109c23",
      "id": "f94c2b36-a683-406d-8dd7-8f25b20b1b94",
      "source": {
        "execution_id": "834ee14f-4bd8-4e3d-ae57-b5a3daaced70",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "0c12ef422474590b519c5e01f78adaf88bf932a9eabff010b1234c6922109c23",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.07182v1.pdf",
      "size": 5383942
    },
    "source": {
      "execution_id": "d36f318e-5755-418a-90f7-e23a7550ce1d",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 12,
      "producer": "pikepdf 8.15.1",
      "title": "PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization",
      "version": "1.7"
    },
    "source": {
      "execution_id": "ed844a9e-458e-4f44-af9e-5273da5171da",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}