{
  "annotation_id": "d9003b5b-247d-4d4f-b45d-a1b5c186ef8b",
  "date_created": "2026-02-17T05:53:05.070000Z",
  "date_modified": "2026-02-17T05:53:05.070000Z",
  "file_hash": "4e68d7f546b139694f4a91fbdb6b3eef869dbdc6e0c00112b0329e1fff954403",
  "private": false,
  "record": {
    "abstract": "This work investigates how measuring information entropy of text can be used to estimate its readability. We propose a visualization framework that can be used to approximate information entropy of text using multiple language models and visualize the result. The end goal is to use this method to estimate and improve readability and clarity of administrative or bureaucratic texts. Our toolset is available as a libre software on https://github.com/ufal/Glitter.",
    "arxiv_id": "2601.05411",
    "authors": [
      "Jan \u010cern\u00fd",
      "Ivana Kvapil\u00edkov\u00e1",
      "Silvie Cinkov\u00e1"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts",
    "url": "https://arxiv.org/abs/2601.05411",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "898fea02-aa01-42da-b7c0-0ad5d13575f9",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}