2601.10407v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:23.671000Z",
      "hash": "f462c6517ce66f59451159feea2441af5ac122fa90df6a3694bee7f4296446c6",
      "id": "b3d65146-7493-4c15-9b47-26645cc8acda",
      "source": {
        "execution_id": "0a511070-06eb-4b50-833b-7ad1fe1ad9d6",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "f462c6517ce66f59451159feea2441af5ac122fa90df6a3694bee7f4296446c6",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.10407v1.pdf",
      "size": 316002
    },
    "source": {
      "execution_id": "cd4b4e01-8a0c-495f-957b-c55dfdaa9fc7",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 13,
      "producer": "pikepdf 8.15.1",
      "title": "CS-GBA: A Critical Sample-based Gradient-guided Backdoor Attack for Offline Reinforcement Learning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "41b877b7-f18f-4dae-85a5-7847895f5275",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}