2601.06874v2.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.664000Z",
      "hash": "fbec94692b8df347651187d62a1596c7b022c3d41598693ec868ec5827153a7e",
      "id": "50b2a34c-6847-40c9-b379-ab92032c731b",
      "source": {
        "execution_id": "6a1fddcf-1123-400e-9f87-fcd5d99afd13",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "fbec94692b8df347651187d62a1596c7b022c3d41598693ec868ec5827153a7e",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06874v2.pdf",
      "size": 15146873
    },
    "source": {
      "execution_id": "b37cb206-17ed-44d8-b377-aa33d07d52fb",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 11,
      "producer": "pikepdf 8.15.1",
      "title": "MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation",
      "version": "1.7"
    },
    "source": {
      "execution_id": "bd5dc9ab-b11f-4bac-8593-a638a076d60f",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}