{"work":{"id":"26c3b627-7e97-40d7-bab3-020936b8196b","openalex_id":null,"doi":null,"arxiv_id":"2308.13418","raw_key":null,"title":"Nougat: Neural Optical Understanding for Academic Documents","authors":null,"authors_text":"Lukas Blecher, Guillem Cucurull, Thomas Scialom, Robert Stojnic","year":2023,"venue":"cs.LG","abstract":"Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs. However, the PDF format leads to a loss of semantic information, particularly for mathematical expressions. We propose Nougat (Neural Optical Understanding for Academic Documents), a Visual Transformer model that performs an Optical Character Recognition (OCR) task for processing scientific documents into a markup language, and demonstrate the effectiveness of our model on a new dataset of scientific documents. The proposed approach offers a promising solution to enhance the accessibility of scientific knowledge in the digital age, by bridging the gap between human-readable documents and machine-readable text. We release the models and code to accelerate future work on scientific text recognition.","external_url":"https://arxiv.org/abs/2308.13418","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-06-28T20:42:37.879641+00:00","pith_arxiv_id":"2308.13418","created_at":"2026-05-10T12:10:22.244011+00:00","updated_at":"2026-06-28T20:42:37.879641+00:00","title_quality_ok":true,"display_title":"Nougat: Neural Optical Understanding for Academic Documents","render_title":"Nougat: Neural Optical Understanding for Academic Documents"},"hub":{"state":{"work_id":"26c3b627-7e97-40d7-bab3-020936b8196b","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":31,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2024-03-08T18:46:00+00:00","last_pith_cited_at":"2026-05-30T21:54:02+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-29T17:19:05.100730+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":6},{"context_role":"method","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"use_method","n":2},{"context_polarity":"baseline","n":1},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}