{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","arxiv_id":"2111.15664","date":"2021-11-30","proceeding":null,"authors":["Geewook Kim","Teakgyu Hong","Moonbin Yim","Jeongyeon Nam","Jinyoung Park","Jinyeong Yim","Wonseok Hwang","Sangdoo Yun","Dongyoon Han","Seunghyun Park"],"abstract":"Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document. Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs. Although such OCR-based approaches have shown promising performance, they suffer from 1) high computational costs for using OCR; 2) inflexibility of OCR models on languages or types of document; 3) OCR error propagation to the subsequent process. To address these issues, in this paper, we introduce a novel OCR-free VDU model named Donut, which stands for Document understanding transformer. As the first step in OCR-free VDU research, we propose a simple architecture (i.e., Transformer) with a pre-training objective (i.e., cross-entropy loss). Donut is conceptually simple yet effective. Through extensive experiments and analyses, we show a simple OCR-free VDU model, Donut, achieves state-of-the-art performances on various VDU tasks in terms of both speed and accuracy. In addition, we offer a synthetic data generator that helps the model pre-training to be flexible in various languages and domains. The code, trained model and synthetic data are available at https://github.com/clovaai/donut.","url_abs":"https://arxiv.org/abs/2111.15664v5","url_pdf":"https://arxiv.org/pdf/2111.15664v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/clovaai/donut","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/impira/docquery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/2023-MindSpore-1/ms-code-2/tree/main/OCRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/MindCode-4/code-3/tree/main/donut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"donut-document-understanding-transformer","repo_url":"https://github.com/code-implementation1/Code9/tree/main/OCRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"document-image-classification","task_name":"Document Image Classification"},{"task_slug":"key-value-pair-extraction","task_name":"Key-value Pair Extraction"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/document-image-classification-on-rvl-cdip","task":"Document Image Classification","dataset":"RVL-CDIP","model":"Donut","rank_in_archive_order":10,"of":31,"metrics":{"Accuracy":"95.3%"},"uses_additional_data":false},{"leaderboard":"/sota/key-value-pair-extraction-on-rfund-en","task":"Key-value Pair Extraction","dataset":"RFUND-EN","model":"Donut","rank_in_archive_order":13,"of":13,"metrics":{"key-value pair F1":"24.54"},"uses_additional_data":false},{"leaderboard":"/sota/key-value-pair-extraction-on-sibr","task":"Key-value Pair Extraction","dataset":"SIBR","model":"Donut","rank_in_archive_order":7,"of":7,"metrics":{"key-value pair F1":"17.26"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"Donut","rank_in_archive_order":29,"of":33,"metrics":{"ANLS":"0.675"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.15664","atlas_url":"https://app.syntology.ai/?focus=2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2111.15664"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2111.15664"},"call":"get_harvested_code_for_paper(arxiv_id=\"2111.15664\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2111.15664"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.15664\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.15664"},"call":"get_concepts_for_paper(arxiv_id=\"2111.15664\")"}],"by_repo":[{"repo":"clovaai/donut","kind":"official","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"impira/docquery","kind":"listed","samples":8,"ran":4,"instrument":0,"unverified":4},{"repo":"2023-MindSpore-1/ms-code-2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindCode-4/code-3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2406.18321"],"harvested_for_calls":[{"arxiv_id":"2406.18321","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.18321"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.18321\")"}]},{"repo":"code-implementation1/Code9","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2111.15664.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2111.15664.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clovaai/donut","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code9/tree/main/OCRNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-2/tree/main/OCRNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/impira/docquery","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-3/tree/main/donut","reach":null}],"summary":{"ran":5,"unverified":4},"n_samples":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":1,"ran":1,"n_ran_checked":1,"n_instrument":0,"repositories":1},"listed":{"samples":8,"ran":4,"n_ran_checked":4,"n_instrument":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"5af813087bf4d28a","code_sha256_prefix":"5af813087bf4d28a","entry":"decode_spans","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/qa_helpers.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/qa_helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"start:ndarray/2/float, end:ndarray/2/float, topk:int/0/int, max_answer_len:int/0/int, undesired_tokens:ndarray/1/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5af813087bf4d28a"}},{"code_sha256":"74ec9de19aac6a0c","code_sha256_prefix":"74ec9de19aac6a0c","entry":"donut_token2json","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/pipeline_document_classification.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/pipeline_document_classification.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer:MockTokenizer/0/?, tokens:str/0/str, is_inner_value:bool/0/bool","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"74ec9de19aac6a0c"}},{"code_sha256":"5df09cd2222c8bdc","code_sha256_prefix":"5df09cd2222c8bdc","entry":"get_logger","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/config.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/config.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prefix:str/0/str","fixture_out_type":"Logger","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":"/code/get-logger","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5df09cd2222c8bdc"}},{"code_sha256":"263020461a3e369d","code_sha256_prefix":"263020461a3e369d","entry":"load_json","repo":"clovaai/donut","repo_kind":"official","path":"donut/util.py","file_url":"https://github.com/clovaai/donut/blob/HEAD/donut/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"json_path:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/load-json","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"263020461a3e369d"}},{"code_sha256":"ad692f1231b24538","code_sha256_prefix":"ad692f1231b24538","entry":"normalize_box","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/pipeline_document_question_answering.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/pipeline_document_question_answering.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"box:list/1/int, width:int/0/int, height:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","retrieve_with":{"tool":"get_code","code_sha256":"ad692f1231b24538"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ad692f1231b24538"}},{"code_sha256":"0a993549920c0550","code_sha256_prefix":"0a993549920c0550","entry":"apply_tesseract","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/pipeline_document_question_answering.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/pipeline_document_question_answering.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0a993549920c0550"}},{"code_sha256":"67438118b555068e","code_sha256_prefix":"67438118b555068e","entry":"main","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/cmd/__main__.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/cmd/__main__.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/main","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"67438118b555068e"}},{"code_sha256":"c783979082342a7f","code_sha256_prefix":"c783979082342a7f","entry":"pipeline","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/transformers_patch.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/transformers_patch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/pipeline","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c783979082342a7f"}},{"code_sha256":"7239c77e40da43e7","code_sha256_prefix":"7239c77e40da43e7","entry":"select_starts_ends","repo":"impira/docquery","repo_kind":"listed","path":"src/docquery/ext/qa_helpers.py","file_url":"https://github.com/impira/docquery/blob/HEAD/src/docquery/ext/qa_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7239c77e40da43e7"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d9a864cc9d4a8cbc1d9eedfcb6b64518f3ea568caa1d9eef1b3081c964bda30c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}