2601.05531v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:05.115000Z",
      "hash": "8247bb6904d8b84daae657c441174d6931eee2a154e6958dc8dd3ff1bc531015",
      "id": "0e5fafc8-f1f9-4a91-9684-0e7631ebdddc",
      "source": {
        "execution_id": "a7c2022f-4a2d-4617-a2c5-ec3d14355125",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "8247bb6904d8b84daae657c441174d6931eee2a154e6958dc8dd3ff1bc531015",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.05531v1.pdf",
      "size": 825648
    },
    "source": {
      "execution_id": "a3088894-4557-487c-9ee4-25dd2b1f5638",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 23,
      "producer": "pikepdf 8.15.1",
      "title": "DNATokenizer: A GPU-First Byte-to-Identifier Tokenizer for High-Throughput DNA Language Models",
      "version": "1.7"
    },
    "source": {
      "execution_id": "64982bb6-5cbc-4710-a1cc-099c6d2d893e",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}