{
 "id": "Cognitive-Lab/NayanaOCRBench_Natural",
 "owner": "Cognitive-Lab",
 "name": "NayanaOCRBench_Natural",
 "downloads": 220,
 "likes": 0,
 "last_modified": "2026-09-17T15:28:30.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-to-text",
  "image-text-to-text"
 ],
 "citation": "@inproceedings{kolavi2025nayanaocr,\n  title     = {Nayana {OCR}: A Scalable Framework for Document {OCR} in Low-Resource Languages},\n  author    = {Kolavi, Adithya S. and Samarth, P. and Jain, Vyoman},\n  booktitle = {Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC), NAACL},\n  year      = {2025}, pages = {86--103}, url = {https://aclanthology.org/2025.lm4uc-1.11/}\n}\n@inproceedings{kolavi2025nayana,\n  title     = {Nayana: A Foundation for Document-Centric Vision-Language Models via Multi-Task, Multimodal, and Multilingual Data Synthesis},\n  author    = {Kolavi, Adithya S. and Samarth, P. and Jain, Vyoman},\n  booktitle = {ICCV Workshops (CV4DC)}, year = {2025}, pages = {1678--1687}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "2684870ad1a0ba271ed56c31e19cb05a6b78c291",
 "stated_evidence": "https://huggingface.co/datasets/Cognitive-Lab/NayanaOCRBench_Natural/blob/2684870ad1a0ba271ed56c31e19cb05a6b78c291/README.md",
 "file_evidence": "https://huggingface.co/datasets/Cognitive-Lab/NayanaOCRBench_Natural/tree/2684870ad1a0ba271ed56c31e19cb05a6b78c291",
 "card_nc": false
}