2601.07737v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:12.650000Z",
      "hash": "5b4cbd5d4bc7e41be82ea73fafc2a1c58f09fff410b3598f6217491ae303e6e1",
      "id": "7214f666-ae5d-46ff-964c-c01fb54b68b3",
      "source": {
        "execution_id": "5d9efcf4-63ee-42e6-b705-dce9892d6e52",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "5b4cbd5d4bc7e41be82ea73fafc2a1c58f09fff410b3598f6217491ae303e6e1",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.07737v1.pdf",
      "size": 764236
    },
    "source": {
      "execution_id": "aa8733bb-9909-45fc-a575-f7f8f808c3c4",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 33,
      "producer": "pikepdf 8.15.1",
      "title": "Evaluating the encoding competence of visual language models using uncommon actions",
      "version": "1.7"
    },
    "source": {
      "execution_id": "e4ed0b19-a991-4fb6-9f81-ce3cd4a2ab71",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}