2601.09215v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:20.213000Z",
      "hash": "93bf7bcd8d19f1edb3f4d22a4021ae63182a13de11f8b9e40b663e3c2ae6730c",
      "id": "be689acf-29eb-4c64-a2f8-cbfdf6ae42b7",
      "source": {
        "execution_id": "3a471062-4051-4c7e-a5d8-032515ba92fc",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "93bf7bcd8d19f1edb3f4d22a4021ae63182a13de11f8b9e40b663e3c2ae6730c",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09215v1.pdf",
      "size": 11176313
    },
    "source": {
      "execution_id": "2524a07e-0642-4312-b25d-271d4d365f67",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 26,
      "producer": "pikepdf 8.15.1",
      "title": "UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "6d640396-0244-4a66-aee6-aacc493dfd6b",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}