2601.16623v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "28a5842b450d4f15a794e292459127edeef81b5397b1f94f7901e8c36b0de737",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.16623v1.pdf",
      "size": 992288
    },
    "source": {
      "execution_id": "5b6b3533-9989-4bdb-8c6d-9f1feb674306",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "creation_date": "2026-01-26T01:33:42Z",
      "keywords": [
        "Lexical normalization",
        "Multilingual and Asian languages",
        "Generative models",
        "Benchmark datasets"
      ],
      "modified_date": "2026-01-26T01:33:42Z",
      "page_count": 19,
      "producer": "pikepdf 8.15.1",
      "title": "MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages",
      "version": "1.7"
    },
    "source": {
      "execution_id": "f87fc564-5164-43c0-b5d1-e07ba5422084",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}