2601.07290v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:12.656000Z",
      "hash": "630b3ce9d0ddbc05ff395d60f9bf62c11045d9055be1dff2e0df0916c03f7ca3",
      "id": "07a426f3-1cbe-402c-8267-3016d700fb87",
      "source": {
        "execution_id": "76f28e50-ec8c-445e-9fed-8b1f124a1972",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "630b3ce9d0ddbc05ff395d60f9bf62c11045d9055be1dff2e0df0916c03f7ca3",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.07290v1.pdf",
      "size": 9281679
    },
    "source": {
      "execution_id": "48d9c83d-2aee-41b2-ac59-172c0166c493",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 23,
      "producer": "pikepdf 8.15.1",
      "title": "VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding",
      "version": "1.7"
    },
    "source": {
      "execution_id": "ce8866e6-6a57-4055-af75-d6cf744fd4e6",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}