2601.11644v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "f73d591158c762511a4e6d3ab973edadb5e1437e0ffb68e908c512e367dafde0",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.11644v1.pdf",
      "size": 24339260
    },
    "source": {
      "execution_id": "f605c065-f08c-4a00-b7e2-5a641c7f8a15",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 9,
      "producer": "pikepdf 8.15.1",
      "title": "Predicting When to Trust Vision-Language Models for Spatial Reasoning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "b0fe331f-7cd6-4299-a95d-85808dda4d6f",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}