2601.06474v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.035000Z",
      "hash": "c74db52095393b29fd27955bda734165ad1ba4f99076f8562cfce4716ac0fbae",
      "id": "08822d3e-7848-4351-8838-580d41261d9b",
      "source": {
        "execution_id": "18b5f804-1369-4624-9e7c-838fa5617ea4",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "c74db52095393b29fd27955bda734165ad1ba4f99076f8562cfce4716ac0fbae",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06474v1.pdf",
      "size": 1663216
    },
    "source": {
      "execution_id": "c3d82de2-126f-4809-ba5e-a44c6d09525e",
      "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": "caed18c0-f31a-4bd9-a566-7cbaf47422ef",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}