2601.06603v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:07.774000Z",
      "hash": "9912a6d8b14ef0f7aee3af90a125d139ff1bbe9f7b48e94676a935c7e5f60a64",
      "id": "88aa028b-f599-4f64-a94e-155d45376434",
      "source": {
        "execution_id": "82dee748-0920-4134-b512-cb753abaa12b",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "9912a6d8b14ef0f7aee3af90a125d139ff1bbe9f7b48e94676a935c7e5f60a64",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06603v1.pdf",
      "size": 648252
    },
    "source": {
      "execution_id": "769db946-5216-4fea-b4a3-393df2a521c2",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 10,
      "producer": "pikepdf 8.15.1",
      "title": "N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs",
      "version": "1.7"
    },
    "source": {
      "execution_id": "eb836e2e-2ddf-4bb4-adde-f531dea4ffee",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}