2601.09239v2.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:20.511000Z",
      "hash": "d0c3e2a0108449635446bd669b5617ec3893018dc8e81986d388b239e54dfb7b",
      "id": "90b05f95-c226-4d14-ae44-ba5949d9bce3",
      "source": {
        "execution_id": "3b6a07ed-dfa1-4d85-a9a2-e2e0e5cd80f0",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "d0c3e2a0108449635446bd669b5617ec3893018dc8e81986d388b239e54dfb7b",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09239v2.pdf",
      "size": 779484
    },
    "source": {
      "execution_id": "f1203cbc-400e-4163-8af1-30af691638f3",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 14,
      "producer": "pikepdf 8.15.1",
      "title": "DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion",
      "version": "1.7"
    },
    "source": {
      "execution_id": "59694cb7-31b7-4e3c-b74a-7e0b5bb55465",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}