2601.06566v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:07.769000Z",
      "hash": "a3cda78c9be5a4a110462170ce742d2acdf849c92c32e81b6938904caa32561c",
      "id": "453afb86-2dcf-4d8c-9734-aab7b9f6e80d",
      "source": {
        "execution_id": "60bd0c76-359b-4515-96d6-d1f4f7443559",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "a3cda78c9be5a4a110462170ce742d2acdf849c92c32e81b6938904caa32561c",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06566v1.pdf",
      "size": 724793
    },
    "source": {
      "execution_id": "43624e94-3409-49f3-be1a-26aea979412e",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 8,
      "producer": "pikepdf 8.15.1",
      "title": "QCaption: Video Captioning and Q\u0026A through Fusion of Large Multimodal Models",
      "version": "1.7"
    },
    "source": {
      "execution_id": "709808f6-3c5f-4d52-9497-de443b4813fc",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}