2601.09954v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:24.373000Z",
      "hash": "7a0272ca983568bb2339302aad7499a795f73b847488679355a64e133cec1b44",
      "id": "385a9b0b-2a30-4a03-aaf8-257ad9d8e7ee",
      "source": {
        "execution_id": "90887a7f-1a10-4f42-b615-7108b4714634",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "7a0272ca983568bb2339302aad7499a795f73b847488679355a64e133cec1b44",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09954v1.pdf",
      "size": 1826330
    },
    "source": {
      "execution_id": "1c7d2dbb-ae9a-4179-b11f-a05ccbf90262",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 10,
      "producer": "pikepdf 8.15.1",
      "title": "The Spatial Blindspot of Vision-Language Models",
      "version": "1.7"
    },
    "source": {
      "execution_id": "2e5c89d4-b46b-4282-b9f9-7b11a55dfd47",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}