{
 "id": "Dharma-AI/DharmaOCR-Benchmark",
 "owner": "Dharma-AI",
 "name": "DharmaOCR-Benchmark",
 "downloads": 470,
 "likes": 6,
 "last_modified": "2026-07-22T00:31:45.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "dharmaocr-benchmark-license",
 "licence_link": "LICENSE",
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-text-to-text"
 ],
 "citation": "@misc{cardoso2026dharmaocrspecializedsmalllanguage,\n      title={DharmaOCR: Specialized Small Language Models for Structured OCR that outperform Open-Source and Commercial Baselines}, \n      author={Gabriel Pimenta de Freitas Cardoso and Caio Lucas da Silva Chacon and Jonas Felipe da Fonseca Oliveira and Paulo Henrique de Medeiros Araujo},\n      year={2026},\n      eprint={2604.14314},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV},\n      url={https://arxiv.org/abs/2604.14314}, \n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "a46b63c2ebe48da14d052ede79873454597ff1a1",
 "stated_evidence": "https://huggingface.co/datasets/Dharma-AI/DharmaOCR-Benchmark/blob/a46b63c2ebe48da14d052ede79873454597ff1a1/README.md",
 "file_evidence": "https://huggingface.co/datasets/Dharma-AI/DharmaOCR-Benchmark/blob/a46b63c2ebe48da14d052ede79873454597ff1a1/LICENSE",
 "card_nc": false
}