2601.09089v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:20.238000Z",
      "hash": "ca57b0dea729f113fd753ae217e01f1737fc6b4114dcab0329927510f20aaf32",
      "id": "9385c33f-54aa-45d8-906b-9a69fce04b9c",
      "source": {
        "execution_id": "3a483f3d-0330-4117-812c-f1ee91f5f47b",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "ca57b0dea729f113fd753ae217e01f1737fc6b4114dcab0329927510f20aaf32",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09089v1.pdf",
      "size": 2472088
    },
    "source": {
      "execution_id": "4e53a2f5-5b3b-4d1c-bc4c-699d3ad4f4d7",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 39,
      "producer": "pikepdf 8.15.1",
      "title": "SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding",
      "version": "1.7"
    },
    "source": {
      "execution_id": "90efb2d3-40e4-4112-9585-3466a7774694",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}