2601.09851v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:23.485000Z",
      "hash": "7169acced29ca148dd288a2ca4d60623fa03dfdc2c1ebe99e05d0a28ffdd3826",
      "id": "b89f2ebe-7892-4acf-b05f-fef9fd369fa7",
      "source": {
        "execution_id": "68a4c4c1-cf8a-47b3-9142-7f1268a76666",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "7169acced29ca148dd288a2ca4d60623fa03dfdc2c1ebe99e05d0a28ffdd3826",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09851v1.pdf",
      "size": 2103337
    },
    "source": {
      "execution_id": "5cd4d4bf-4928-4336-b7df-0acf60c2d712",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 15,
      "producer": "pikepdf 8.15.1",
      "title": "ViSIL: Unified Evaluation of Information Loss in Multimodal Video Captioning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "fc4fda40-57c8-436b-a527-91a10d8bc3cd",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}