2601.08871v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:20.178000Z",
      "hash": "c8dc2bb38db0a7c1a0eb593c87b5700bde889a33ca3d569de6b19c01c3bd4542",
      "id": "66356833-a384-47ed-a9ce-daab8d668aa8",
      "source": {
        "execution_id": "82e4f18e-0e10-461c-a24d-ff89103adf1f",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "c8dc2bb38db0a7c1a0eb593c87b5700bde889a33ca3d569de6b19c01c3bd4542",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.08871v1.pdf",
      "size": 726236
    },
    "source": {
      "execution_id": "0f1726d9-4b2a-4f93-b502-08ec0c339c60",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 5,
      "producer": "pikepdf 8.15.1",
      "title": "Semantic visually-guided acoustic highlighting with large vision-language models",
      "version": "1.7"
    },
    "source": {
      "execution_id": "7ccad6e0-8479-4338-bb80-a96a951a4c57",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}