{"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":"/task/key-information-extraction","name":"Key Information Extraction","slug":"key-information-extraction","description_markdown":"Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":74,"papers_with_code":40,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":12,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/key-information-extraction-on-cord","slug":"key-information-extraction-on-cord","dataset":"CORD","dataset_url":"/dataset/cord","rows_in_archive":9,"metrics":["F1"],"first_row_in_archive_order":{"model":"RORE (GeoLayoutLM)","paper_title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","paper_url":"/paper/modeling-layout-reading-order-as-ordering","paper_date":"2024-09-29","arxiv_id":"2409.19672","code_links":[{"title":"chongzhangFDU/ROOR","url":"https://github.com/chongzhangFDU/ROOR"}],"syntology":null}},{"leaderboard":"/sota/key-information-extraction-on-sroie","slug":"key-information-extraction-on-sroie","dataset":"SROIE","dataset_url":"/dataset/sroie","rows_in_archive":5,"metrics":["F1","Accuracy"],"first_row_in_archive_order":{"model":"LayoutLMv2LARGE (Excluding OCR mismatch)","paper_title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","paper_url":"/paper/layoutlmv2-multi-modal-pre-training-for","paper_date":"2020-12-29","arxiv_id":"2012.14740","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutlmv2"},{"title":"facebookresearch/data2vec_vision","url":"https://github.com/facebookresearch/data2vec_vision"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/layoutlmv2"},{"title":"MS-P3/code3","url":"https://github.com/MS-P3/code3/tree/main/layoutlmv2"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/LayoutLMv2"}],"syntology":null}},{"leaderboard":"/sota/key-information-extraction-on-kleister-nda","slug":"key-information-extraction-on-kleister-nda","dataset":"Kleister NDA","dataset_url":"/dataset/kleister-nda","rows_in_archive":3,"metrics":["F1"],"first_row_in_archive_order":{"model":"LayoutLMv2LARGE","paper_title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","paper_url":"/paper/layoutlmv2-multi-modal-pre-training-for","paper_date":"2020-12-29","arxiv_id":"2012.14740","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/layoutlmv2"},{"title":"facebookresearch/data2vec_vision","url":"https://github.com/facebookresearch/data2vec_vision"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/layoutlmv2"},{"title":"MS-P3/code3","url":"https://github.com/MS-P3/code3/tree/main/layoutlmv2"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv2"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/LayoutLMv2"}],"syntology":null}},{"leaderboard":"/sota/key-information-extraction-on-ephoie","slug":"key-information-extraction-on-ephoie","dataset":"EPHOIE","dataset_url":"/dataset/ephoie","rows_in_archive":1,"metrics":["Average F1"],"first_row_in_archive_order":{"model":"LayoutLMv3","paper_title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","paper_url":"/paper/layoutlmv3-pre-training-for-document-ai-with","paper_date":"2022-04-18","arxiv_id":"2204.08387","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/layoutlmv3"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/layoutlmv3"},{"title":"MindSpore-scientific-2/code-14","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv3"}],"syntology":null}},{"leaderboard":"/sota/key-information-extraction-on-etd500","slug":"key-information-extraction-on-etd500","dataset":"ETD500","dataset_url":"/dataset/etd500","rows_in_archive":1,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"CRF-visual","paper_title":"Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations","paper_url":"/paper/automatic-metadata-extraction-incorporating","paper_date":"2021-07-01","arxiv_id":"2107.00516","code_links":[{"title":"lamps-lab/ETDMiner","url":"https://github.com/lamps-lab/ETDMiner"},{"title":"lamps-lab/AutoMeta","url":"https://github.com/lamps-lab/AutoMeta"}],"syntology":null}},{"leaderboard":"/sota/key-information-extraction-on-simara","slug":"key-information-extraction-on-simara","dataset":"SIMARA","dataset_url":"/dataset/simara","rows_in_archive":1,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"DAN","paper_title":"SIMARA: a database for key-value information extraction from full pages","paper_url":"/paper/simara-a-database-for-key-value-information","paper_date":"2023-04-26","arxiv_id":"2304.13606","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/sroie","name":"SROIE","full_name":"","num_papers_in_archive":105},{"url":"/dataset/cord","name":"CORD","full_name":"Consolidated Receipt Dataset for Post-OCR Parsing","num_papers_in_archive":100},{"url":"/dataset/ephoie","name":"EPHOIE","full_name":"phtnsantader@gmail.com","num_papers_in_archive":21},{"url":"/dataset/kleister-nda","name":"Kleister NDA","full_name":"","num_papers_in_archive":17},{"url":"/dataset/sibr","name":"SIBR","full_name":"SIBR Dataset for VIE in the Wild","num_papers_in_archive":14},{"url":"/dataset/docile","name":"DocILE","full_name":"","num_papers_in_archive":11},{"url":"/dataset/information-extraction-from-tables","name":"Information Extraction from Tables","full_name":"Extraction materials compositions from tables of materials science research papers","num_papers_in_archive":3},{"url":"/dataset/etd500","name":"ETD500","full_name":"","num_papers_in_archive":2},{"url":"/dataset/simara","name":"SIMARA","full_name":"SIMARA: a database for key-value information extraction from full-page handwritten documents","num_papers_in_archive":2},{"url":"/dataset/poie","name":"POIE","full_name":"Products for OCR and Information Extraction","num_papers_in_archive":1},{"url":"/dataset/somd","name":"SOMD","full_name":"SOftware Mention Detection","num_papers_in_archive":1},{"url":"/dataset/arf","name":"ARF","full_name":"Artificial Relationships in Fiction","num_papers_in_archive":0}],"subtasks":[{"url":"/task/key-value-pair-extraction","name":"Key-value Pair Extraction"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":74,"of":74,"of_with_code":40,"tagged_in_all":74,"counts":{"archive_papers_tagged":74,"with_a_code_link":40,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":74,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/layoutlm-pre-training-of-text-and-layout-for","slug":"layoutlm-pre-training-of-text-and-layout-for","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","date":"2019-12-31","arxiv_id":"1912.13318","repositories_listed":19,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layoutlm-pre-training-of-text-and-layout-for#ran","syntology_url":"https://syntology.ai/paper/1912.13318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.13318"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","repositories_listed":9,"syntology":null},{"url":"/paper/lilt-a-simple-yet-effective-language","slug":"lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lilt-a-simple-yet-effective-language#ran","syntology_url":"https://syntology.ai/paper/2202.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13669"}},"official":{"repos":["jpwang/lilt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/layoutlmv3-pre-training-for-document-ai-with","slug":"layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","repositories_listed":4,"syntology":null},{"url":"/paper/xformparser-a-simple-and-effective-multimodal","slug":"xformparser-a-simple-and-effective-multimodal","title":"XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser","date":"2024-05-27","arxiv_id":"2405.17336","repositories_listed":2,"syntology":null},{"url":"/paper/reading-order-matters-information-extraction","slug":"reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/bros-a-layout-aware-pre-trained-language","slug":"bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","arxiv_id":"2108.04539","repositories_listed":2,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bros-a-layout-aware-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2108.04539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04539"}},"official":{"repos":["clovaai/bros"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-metadata-extraction-incorporating","slug":"automatic-metadata-extraction-incorporating","title":"Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations","date":"2021-07-01","arxiv_id":"2107.00516","repositories_listed":2,"syntology":null},{"url":"/paper/spatial-dual-modality-graph-reasoning-for-key","slug":"spatial-dual-modality-graph-reasoning-for-key","title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","date":"2021-03-26","arxiv_id":"2103.14470","repositories_listed":2,"syntology":null},{"url":"/paper/pick-processing-key-information-extraction","slug":"pick-processing-key-information-extraction","title":"PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks","date":"2020-04-16","arxiv_id":"2004.07464","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pick-processing-key-information-extraction#ran","syntology_url":"https://syntology.ai/paper/2004.07464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07464"}},"official":{"repos":["wenwenyu/PICK-pytorch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/paddleocr-3-0-technical-report","slug":"paddleocr-3-0-technical-report","title":"PaddleOCR 3.0 Technical Report","date":"2025-07-08","arxiv_id":"2507.05595","repositories_listed":1,"syntology":null},{"url":"/paper/class-agnostic-region-of-interest-matching-in","slug":"class-agnostic-region-of-interest-matching-in","title":"Class-Agnostic Region-of-Interest Matching in Document Images","date":"2025-06-26","arxiv_id":"2506.21055","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-v2-structured-points-of-thought","slug":"omniparser-v2-structured-points-of-thought","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","date":"2025-02-22","arxiv_id":"2502.16161","repositories_listed":1,"syntology":null},{"url":"/paper/graphrevisedie-multimodal-information","slug":"graphrevisedie-multimodal-information","title":"GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network","date":"2024-10-02","arxiv_id":"2410.01160","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-layout-reading-order-as-ordering","slug":"modeling-layout-reading-order-as-ordering","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","date":"2024-09-29","arxiv_id":"2409.19672","repositories_listed":1,"syntology":null},{"url":"/paper/information-extraction-from-visually-rich-1","slug":"information-extraction-from-visually-rich-1","title":"Information Extraction from Visually Rich Documents Using Directed Weighted Graph Neural Network","date":"2024-09-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-bounding-box-is-worth-one-token","slug":"a-bounding-box-is-worth-one-token","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","date":"2024-07-02","arxiv_id":"2407.01976","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bounding-box-is-worth-one-token#ran","syntology_url":"https://syntology.ai/paper/2407.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01976"}},"official":{"repos":["laytextllm/laytextllm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kvp10k-a-comprehensive-dataset-for-key-value","slug":"kvp10k-a-comprehensive-dataset-for-key-value","title":"KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents","date":"2024-05-01","arxiv_id":"2405.00505","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-a-unified-framework-for-text","slug":"omniparser-a-unified-framework-for-text","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","date":"2024-03-28","arxiv_id":"2403.19128","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omniparser-a-unified-framework-for-text#ran","syntology_url":"https://syntology.ai/paper/2403.19128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19128"}},"official":{"repos":["alibabaresearch/advancedliteratemachinery"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/textmonkey-an-ocr-free-large-multimodal-model","slug":"textmonkey-an-ocr-free-large-multimodal-model","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","date":"2024-03-07","arxiv_id":"2403.04473","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/textmonkey-an-ocr-free-large-multimodal-model#ran","syntology_url":"https://syntology.ai/paper/2403.04473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04473"}},"official":{"repos":["yuliang-liu/monkey"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/different-tastes-of-entities-investigating","slug":"different-tastes-of-entities-investigating","title":"Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations","date":"2024-02-02","arxiv_id":"2402.01423","repositories_listed":1,"syntology":null},{"url":"/paper/peneo-unifying-line-extraction-line-grouping","slug":"peneo-unifying-line-extraction-line-grouping","title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","date":"2024-01-07","arxiv_id":"2401.03472","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-weighted-graph-representation-for","slug":"multimodal-weighted-graph-representation-for","title":"Multimodal weighted graph representation for information extraction from visually rich documents.","date":"2024-01-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-a-unified-framework-for-text-1","slug":"omniparser-a-unified-framework-for-text-1","title":"OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-ocr-capabilities-of-gpt-4v-ision-a","slug":"exploring-ocr-capabilities-of-gpt-4v-ision-a","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","date":"2023-10-25","arxiv_id":"2310.16809","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-ocr-capabilities-of-gpt-4v-ision-a#ran","syntology_url":"https://syntology.ai/paper/2310.16809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16809"}},"official":{"repos":["scut-dlvclab/gpt-4v_ocr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/genkie-robust-generative-multimodal-document","slug":"genkie-robust-generative-multimodal-document","title":"GenKIE: Robust Generative Multimodal Document Key Information Extraction","date":"2023-10-24","arxiv_id":"2310.16131","repositories_listed":1,"syntology":null},{"url":"/paper/amurd-annotated-multilingual-receipts-dataset","slug":"amurd-annotated-multilingual-receipts-dataset","title":"AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and Classification","date":"2023-09-18","arxiv_id":"2309.09800","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-hidden-mystery-of-ocr-in-large","slug":"on-the-hidden-mystery-of-ocr-in-large","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","date":"2023-05-13","arxiv_id":"2305.07895","repositories_listed":1,"syntology":null},{"url":"/paper/information-redundancy-and-biases-in-public","slug":"information-redundancy-and-biases-in-public","title":"Information Redundancy and Biases in Public Document Information Extraction Benchmarks","date":"2023-04-28","arxiv_id":"2304.14936","repositories_listed":1,"syntology":null},{"url":"/paper/geolayoutlm-geometric-pre-training-for-visual","slug":"geolayoutlm-geometric-pre-training-for-visual","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","date":"2023-04-21","arxiv_id":"2304.10759","repositories_listed":1,"syntology":null},{"url":"/paper/form-nlu-dataset-for-the-form-language","slug":"form-nlu-dataset-for-the-form-language","title":"Form-NLU: Dataset for the Form Natural Language Understanding","date":"2023-04-04","arxiv_id":"2304.01577","repositories_listed":1,"syntology":null},{"url":"/paper/docile-benchmark-for-document-information","slug":"docile-benchmark-for-document-information","title":"DocILE Benchmark for Document Information Localization and Extraction","date":"2023-02-11","arxiv_id":"2302.05658","repositories_listed":1,"syntology":null},{"url":"/paper/dosa-a-system-to-accelerate-annotations-on","slug":"dosa-a-system-to-accelerate-annotations-on","title":"DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loop","date":"2022-11-09","arxiv_id":"2211.04934","repositories_listed":1,"syntology":null},{"url":"/paper/pp-structurev2-a-stronger-document-analysis","slug":"pp-structurev2-a-stronger-document-analysis","title":"PP-StructureV2: A Stronger Document Analysis System","date":"2022-10-11","arxiv_id":"2210.05391","repositories_listed":1,"syntology":null},{"url":"/paper/doc2graph-a-task-agnostic-document","slug":"doc2graph-a-task-agnostic-document","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","date":"2022-08-23","arxiv_id":"2208.11168","repositories_listed":1,"syntology":null},{"url":"/paper/mmocr-a-comprehensive-toolbox-for-text","slug":"mmocr-a-comprehensive-toolbox-for-text","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","date":"2021-08-14","arxiv_id":"2108.06543","repositories_listed":1,"syntology":null},{"url":"/paper/key-information-extraction-from-documents","slug":"key-information-extraction-from-documents","title":"Key Information Extraction From Documents: Evaluation And Generator","date":"2021-06-09","arxiv_id":"2106.14624","repositories_listed":1,"syntology":null},{"url":"/paper/icdar2019-competition-on-scanned-receipt-ocr","slug":"icdar2019-competition-on-scanned-receipt-ocr","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","date":"2021-03-18","arxiv_id":"2103.10213","repositories_listed":1,"syntology":null},{"url":"/paper/lambert-layout-aware-language-modeling-using","slug":"lambert-layout-aware-language-modeling-using","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","date":"2020-02-19","arxiv_id":"2002.08087","repositories_listed":1,"syntology":null},{"url":null,"slug":"hallucinations-and-key-information-extraction","title":"Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models","date":"2025-04-27","arxiv_id":"2504.19061","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergency-communication-otfs-based-semantic","title":"Emergency Communication: OTFS-Based Semantic Transmission with Diffusion Noise Suppression","date":"2025-04-10","arxiv_id":"2504.07420","repositories_listed":0,"syntology":null},{"url":null,"slug":"kieval-evaluation-metric-for-document-key","title":"KIEval: Evaluation Metric for Document Key Information Extraction","date":"2025-03-07","arxiv_id":"2503.05488","repositories_listed":0,"syntology":null},{"url":null,"slug":"cc-ocr-a-comprehensive-and-challenging-ocr","title":"CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy","date":"2024-12-03","arxiv_id":"2412.02210","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-the-value-of-templates-rethinking","title":"\"What is the value of {templates}?\" Rethinking Document Information Extraction Datasets for LLMs","date":"2024-10-20","arxiv_id":"2410.15484","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-then-tell-enhancing-key-information","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","date":"2024-09-29","arxiv_id":"2409.19573","repositories_listed":0,"syntology":null},{"url":null,"slug":"vibertgrid-bilstm-crf-multimodal-key","title":"ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents","date":"2024-09-23","arxiv_id":"2409.15004","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-key-information","title":"Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review","date":"2024-07-23","arxiv_id":"2408.06345","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-structured-generation","title":"Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use","date":"2024-05-30","arxiv_id":"2405.20245","repositories_listed":0,"syntology":null},{"url":"/paper/a-layoutlmv3-based-model-for-enhanced","slug":"a-layoutlmv3-based-model-for-enhanced","title":"A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents","date":"2024-04-16","arxiv_id":"2404.10848","repositories_listed":0,"syntology":null},{"url":null,"slug":"realkie-five-novel-datasets-for-enterprise","title":"RealKIE: Five Novel Datasets for Enterprise Key Information Extraction","date":"2024-03-29","arxiv_id":"2403.20101","repositories_listed":0,"syntology":null},{"url":null,"slug":"construction-of-a-syntactic-analysis-map-for","title":"Construction of a Syntactic Analysis Map for Yi Shui School through Text Mining and Natural Language Processing Research","date":"2024-02-16","arxiv_id":"2402.10743","repositories_listed":0,"syntology":null},{"url":"/paper/lapdoc-layout-aware-prompting-for-documents","slug":"lapdoc-layout-aware-prompting-for-documents","title":"LAPDoc: Layout-Aware Prompting for Documents","date":"2024-02-15","arxiv_id":"2402.09841","repositories_listed":0,"syntology":null},{"url":null,"slug":"univie-a-unified-label-space-approach-to","title":"UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents","date":"2024-01-17","arxiv_id":"2401.09220","repositories_listed":0,"syntology":null},{"url":null,"slug":"donut-hole-donut-sparsification-by-harnessing","title":"DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency","date":"2023-11-09","arxiv_id":"2311.05778","repositories_listed":0,"syntology":null},{"url":null,"slug":"vkie-the-application-of-key-information","title":"VKIE: The Application of Key Information Extraction on Video Text","date":"2023-10-18","arxiv_id":"2310.11650","repositories_listed":0,"syntology":null},{"url":null,"slug":"pried-kie-towards-privacy-preserved-document","title":"PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction","date":"2023-10-05","arxiv_id":"2310.03777","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-training-of-a-u-net-based","title":"Data Efficient Training of a U-Net Based Architecture for Structured Documents Localization","date":"2023-10-02","arxiv_id":"2310.00937","repositories_listed":0,"syntology":null},{"url":null,"slug":"ppn-parallel-pointer-based-network-for-key","title":"PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts","date":"2023-07-20","arxiv_id":"2307.10551","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-document-classification-and-key","title":"End-to-End Document Classification and Key Information Extraction using Assignment Optimization","date":"2023-06-01","arxiv_id":"2306.00750","repositories_listed":0,"syntology":null},{"url":"/paper/layoutmask-enhance-text-layout-interaction-in","slug":"layoutmask-enhance-text-layout-interaction-in","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","date":"2023-05-30","arxiv_id":"2305.18721","repositories_listed":0,"syntology":null},{"url":"/paper/dublin-document-understanding-by-language","slug":"dublin-document-understanding-by-language","title":"DUBLIN -- Document Understanding By Language-Image Network","date":"2023-05-23","arxiv_id":"2305.14218","repositories_listed":0,"syntology":null},{"url":"/paper/simara-a-database-for-key-value-information","slug":"simara-a-database-for-key-value-information","title":"SIMARA: a database for key-value information extraction from full pages","date":"2023-04-26","arxiv_id":"2304.13606","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-extraction-from-documents","title":"Information Extraction from Documents: Question Answering vs Token Classification in real-world setups","date":"2023-04-21","arxiv_id":"2304.10994","repositories_listed":0,"syntology":null},{"url":"/paper/pdf-vqa-a-new-dataset-for-real-world-vqa-on","slug":"pdf-vqa-a-new-dataset-for-real-world-vqa-on","title":"PDFVQA: A New Dataset for Real-World VQA on PDF Documents","date":"2023-04-13","arxiv_id":"2304.06447","repositories_listed":0,"syntology":null},{"url":null,"slug":"ncu1415-at-rocling-2022-shared-task-a-light","title":"NCU1415 at ROCLING 2022 Shared Task: A light-weight transformer-based approach for Biomedical Name Entity Recognition","date":"2022-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"key-information-extraction-in-purchase","title":"Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections","date":"2022-10-07","arxiv_id":"2210.03453","repositories_listed":0,"syntology":null},{"url":null,"slug":"rdu-a-region-based-approach-to-form-style","title":"RDU: A Region-based Approach to Form-style Document Understanding","date":"2022-06-14","arxiv_id":"2206.06890","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-representation-learning-in","title":"Relational Representation Learning in Visually-Rich Documents","date":"2022-05-05","arxiv_id":"2205.02411","repositories_listed":0,"syntology":null},{"url":"/paper/relationship-extraction-for-knowledge-graph","slug":"relationship-extraction-for-knowledge-graph","title":"Comparison of biomedical relationship extraction methods and models for knowledge graph creation","date":"2022-01-05","arxiv_id":"2201.01647","repositories_listed":0,"syntology":null},{"url":"/paper/entity-relation-extraction-as-dependency","slug":"entity-relation-extraction-as-dependency","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","date":"2021-10-19","arxiv_id":"2110.09915","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-key-information-extraction-from","title":"One-shot Key Information Extraction from Document with Deep Partial Graph Matching","date":"2021-09-26","arxiv_id":"2109.13967","repositories_listed":0,"syntology":null},{"url":null,"slug":"vibertgrid-a-jointly-trained-multi-modal-2d","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","date":"2021-05-25","arxiv_id":"2105.11672","repositories_listed":0,"syntology":null},{"url":"/paper/kleister-key-information-extraction-datasets","slug":"kleister-key-information-extraction-datasets","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","date":"2021-05-12","arxiv_id":"2105.05796","repositories_listed":0,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/key-information-extraction-on-cord","since_archive":"/sota/key-information-extraction-on-cord#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/task/key-information-extraction/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/key-information-extraction/papers/ran/1","json":"/task/key-information-extraction/papers/ran/1.json","rows":9}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"a675cbac0bc1293b8c8becba9a638387577a3c6b94e98dc7a75257ea2f9d12c9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}