2601.08133v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:15.372000Z",
      "hash": "354f0c8229fe64b654b88984d96ef6ef604b0b131bcefc69b35c3ee6fb62defd",
      "id": "7d9c063c-5521-4b0d-9828-f6260375de1b",
      "source": {
        "execution_id": "15218039-1c2c-4956-82b1-0bd614ab1796",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "354f0c8229fe64b654b88984d96ef6ef604b0b131bcefc69b35c3ee6fb62defd",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.08133v1.pdf",
      "size": 5052110
    },
    "source": {
      "execution_id": "0703be80-dc33-469a-b1ae-92f3eab3d82a",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 11,
      "producer": "pikepdf 8.15.1",
      "title": "How Do Optical Flow and Textual Prompts Collaborate to Assist in Audio-Visual Semantic Segmentation?",
      "version": "1.7"
    },
    "source": {
      "execution_id": "4feecbfb-d5e5-4545-add3-d9407cb8915d",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}