2601.07349v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:12.483000Z",
      "hash": "c9457819d55438b9d9ab9f164ca3a0222aa17c912ed6b46e5a22f0c110e2be47",
      "id": "d45c9407-352c-4299-8057-013b48224830",
      "source": {
        "execution_id": "90175fed-b766-4461-9ad3-95467a8d70ed",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "c9457819d55438b9d9ab9f164ca3a0222aa17c912ed6b46e5a22f0c110e2be47",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.07349v1.pdf",
      "size": 5705191
    },
    "source": {
      "execution_id": "99de8f47-8521-465b-84af-8daca2be1ff1",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 29,
      "producer": "pikepdf 8.15.1",
      "title": "Reward Modeling from Natural Language Human Feedback",
      "version": "1.7"
    },
    "source": {
      "execution_id": "904bc98f-6352-47c6-bf5c-f06b49752abb",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}