2601.06795v2.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.813000Z",
      "hash": "07e3479938e8d174cc6015065276375a1473a7b2689da50f9b4091373b2db772",
      "id": "b6bd3fa3-6cbd-458e-b024-2db04db67479",
      "source": {
        "execution_id": "117f78a2-7457-4f76-ab0f-f69edb82c2fe",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "07e3479938e8d174cc6015065276375a1473a7b2689da50f9b4091373b2db772",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06795v2.pdf",
      "size": 6424182
    },
    "source": {
      "execution_id": "20e28661-c681-403e-9960-43c21a81ca62",
      "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": "15c3a660-d20d-4597-8bf2-c0e69912fd3d",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}