2601.06795v3.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:07.837000Z",
      "hash": "c9925725e6a5b5da0fecfe3dcf4036fdfafa18b5edb8242a42cb3ab8773228de",
      "id": "1155b9e4-4d3c-4d3c-8c07-441778e00e6a",
      "source": {
        "execution_id": "961b68d1-deea-420a-af2f-9302feb13b4d",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "c9925725e6a5b5da0fecfe3dcf4036fdfafa18b5edb8242a42cb3ab8773228de",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06795v3.pdf",
      "size": 6424293
    },
    "source": {
      "execution_id": "6616fef8-074c-4514-a47a-36811a888729",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 12,
      "producer": "pikepdf 8.15.1",
      "title": "GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "d32b719b-9c20-478e-9e65-059246ddba9d",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}