2601.06573v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:07.772000Z",
      "hash": "386db4d95d26bca469bd3c7d6ad71a6e8d4710b5a700ae831d8169028c9cf678",
      "id": "d2a5dd93-1606-4d84-b18f-ffe83abe6a10",
      "source": {
        "execution_id": "d0bbeccb-a27c-4bca-98ff-268cdd283f3e",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "386db4d95d26bca469bd3c7d6ad71a6e8d4710b5a700ae831d8169028c9cf678",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06573v1.pdf",
      "size": 556878
    },
    "source": {
      "execution_id": "796860df-dcae-4c44-88cd-2ba07057aee9",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 7,
      "producer": "pikepdf 8.15.1",
      "title": "QMAVIS: Long Video-Audio Understanding using Fusion of Large Multimodal Models",
      "version": "1.7"
    },
    "source": {
      "execution_id": "77f224bb-5c15-47ba-9533-a9926c26621d",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}