2601.18533v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "bf193d93fee962d4961a7214527446982182f45a5827b3d393895860de6bf5a6",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.18533v1.pdf",
      "size": 986622
    },
    "source": {
      "execution_id": "7f13af20-ed15-490c-af52-6d63f6aaecde",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 19,
      "producer": "pikepdf 8.15.1",
      "title": "From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation",
      "version": "1.7"
    },
    "source": {
      "execution_id": "2251f07f-76eb-42dc-bb15-9054d89c1e4b",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}