2601.14599v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "cf188480f0deab29ef4d35090cde271c210ecdbf605740e47aef2ff5a6e4e3b4",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.14599v1.pdf",
      "size": 6785570
    },
    "source": {
      "execution_id": "0aaead6b-f484-48ca-bc6c-76c3e0c3fdf1",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 13,
      "producer": "pikepdf 8.15.1",
      "title": "Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective",
      "version": "1.7"
    },
    "source": {
      "execution_id": "8fe3f1c1-8f77-4a77-8bff-58572399de23",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}