2601.07182v2.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:11.754000Z",
      "hash": "0affa6c7a1fbf0722092fbe67c4e5c7acc0e0e25fc1e9c96ad5e4b787f45475a",
      "id": "824378a0-6ff2-40c0-9741-670c871371a6",
      "source": {
        "execution_id": "f4baf3a3-c743-4911-9642-8b15229f4bc2",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "0affa6c7a1fbf0722092fbe67c4e5c7acc0e0e25fc1e9c96ad5e4b787f45475a",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.07182v2.pdf",
      "size": 5383942
    },
    "source": {
      "execution_id": "73159f2d-cc79-40a3-8a57-ef98475375f1",
      "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": "092ae513-135e-4eac-ba34-a6935d6d2d5a",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}