2601.06474v2.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.036000Z",
      "hash": "6d0214f16baefa3f87104c0b0ae843608aac1bf4ea953d9c5000678aae60ac38",
      "id": "91bdf768-dc12-4120-b253-ccb8dcae7802",
      "source": {
        "execution_id": "4e9e1ea3-fe32-4126-a784-39195dd76943",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "6d0214f16baefa3f87104c0b0ae843608aac1bf4ea953d9c5000678aae60ac38",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06474v2.pdf",
      "size": 2628010
    },
    "source": {
      "execution_id": "89959d6d-6b83-4c21-bd56-5bb6e6f60011",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 18,
      "producer": "pikepdf 8.15.1",
      "title": "SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "2eaa5681-4996-4830-aa42-7d281a9a7e35",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}