{"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/table-recognition","name":"Table Recognition","slug":"table-recognition","description_markdown":"Table recognition refers to the process of automatically identifying and extracting tabular structures from unstructured data sources such as text documents, images, or scanned documents. The goal of table recognition is to accurately detect the presence of tables within the data and extract their contents, including rows, columns, headers, and cell values.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":50,"papers_with_code":28,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/table-recognition-on-pubtabnet","slug":"table-recognition-on-pubtabnet","dataset":"PubTabNet","dataset_url":"/dataset/pubtabnet","rows_in_archive":13,"metrics":["TEDS (all samples)","TEDS-Struct"],"first_row_in_archive_order":{"model":"MuTabNet","paper_title":"Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition","paper_url":"/paper/multi-cell-decoder-and-mutual-learning-for","paper_date":"2024-04-20","arxiv_id":"2404.13268","code_links":[{"title":"JG1VPP/MuTabNet","url":"https://github.com/JG1VPP/MuTabNet"}],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-table-recognition","slug":"table-recognition-on-table-recognition","dataset":"Table Recognition Challenge mini-test","dataset_url":null,"rows_in_archive":4,"metrics":["TEDS (all samples)","TEDS (simple samples)","TEDS (complex samples)"],"first_row_in_archive_order":{"model":"Re0","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-table-recognition-2","slug":"table-recognition-on-table-recognition-2","dataset":"Table Recognition Challenge test","dataset_url":null,"rows_in_archive":2,"metrics":["TEDS (all samples)","TEDS (simple samples)","TEDS (complex samples)"],"first_row_in_archive_order":{"model":"Habitat-Web","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-icdar2013-table","slug":"table-recognition-on-icdar2013-table","dataset":"ICDAR2013 table structure recognition","dataset_url":null,"rows_in_archive":1,"metrics":["F-Measure"],"first_row_in_archive_order":{"model":"Proposed System (With post- processing)","paper_title":"Guided Table Structure Recognition through Anchor Optimization","paper_url":"/paper/guided-table-structure-recognition-through","paper_date":"2021-04-21","arxiv_id":"2104.10538","code_links":[],"syntology":null}},{"leaderboard":"/sota/table-recognition-on-wtw","slug":"table-recognition-on-wtw","dataset":"WTW","dataset_url":"/dataset/wtw","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"StrucTexTv2 (small)","paper_title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","paper_url":"/paper/structextv2-masked-visual-textual-prediction","paper_date":"2023-03-01","arxiv_id":"2303.00289","code_links":[{"title":"PaddlePaddle/VIMER","url":"https://github.com/PaddlePaddle/VIMER/tree/main/StrucTexT/v2"}],"syntology":null}}],"datasets":[{"url":"/dataset/pubtabnet","name":"PubTabNet","full_name":"PubTabNet","num_papers_in_archive":51},{"url":"/dataset/fintabnet","name":"FinTabNet","full_name":"","num_papers_in_archive":35},{"url":"/dataset/wtw","name":"WTW","full_name":"Wired Table in the Wild","num_papers_in_archive":18},{"url":"/dataset/pubtables-1m","name":"PubTables-1M","full_name":"PubMed Tables One Million","num_papers_in_archive":15},{"url":"/dataset/tncr-dataset","name":"TNCR Dataset","full_name":"Table Net Detection and Classification Dataset","num_papers_in_archive":2},{"url":"/dataset/wikitableset","name":"WikiTableSet","full_name":"Wikipedia Table Image Dataset","num_papers_in_archive":2},{"url":"/dataset/cisol","name":"CISOL","full_name":"Construction Industry Steel Ordering Lists Dataset","num_papers_in_archive":1}],"subtasks":[],"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":50,"of":50,"of_with_code":28,"tagged_in_all":50,"counts":{"archive_papers_tagged":50,"with_a_code_link":28,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":50,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/image-based-table-recognition-data-model-and","slug":"image-based-table-recognition-data-model-and","title":"Image-based table recognition: data, model, and evaluation","date":"2019-11-25","arxiv_id":"1911.10683","repositories_listed":6,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/image-based-table-recognition-data-model-and#ran","syntology_url":"https://syntology.ai/paper/1911.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.10683"}},"official":{"repos":["ibm-aur-nlp/PubTabNet"],"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/rethinking-table-parsing-using-graph-neural","slug":"rethinking-table-parsing-using-graph-neural","title":"Rethinking Table Recognition using Graph Neural Networks","date":"2019-05-31","arxiv_id":"1905.13391","repositories_listed":5,"syntology":null},{"url":"/paper/deep-learning-for-table-detection-and","slug":"deep-learning-for-table-detection-and","title":"Deep learning for table detection and structure recognition: A survey","date":"2022-11-15","arxiv_id":"2211.08469","repositories_listed":3,"syntology":null},{"url":"/paper/icdar-2021-competition-on-scientific","slug":"icdar-2021-competition-on-scientific","title":"ICDAR 2021 Competition on Scientific Literature Parsing","date":"2021-06-08","arxiv_id":"2106.14616","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/icdar-2021-competition-on-scientific#ran","syntology_url":"https://syntology.ai/paper/2106.14616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14616"}},"official":{"repos":["ibm-aur-nlp/PubLayNet","ibm-aur-nlp/PubTabNet","wenwenyu/MASTER-pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pingan-vcgroup-s-solution-for-icdar-2021","slug":"pingan-vcgroup-s-solution-for-icdar-2021","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","date":"2021-05-05","arxiv_id":"2105.01848","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pingan-vcgroup-s-solution-for-icdar-2021#ran","syntology_url":"https://syntology.ai/paper/2105.01848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01848"}},"official":null}},{"url":"/paper/cascadetabnet-an-approach-for-end-to-end","slug":"cascadetabnet-an-approach-for-end-to-end","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","date":"2020-04-27","arxiv_id":"2004.12629","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cascadetabnet-an-approach-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2004.12629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12629"}},"official":{"repos":["DevashishPrasad/CascadeTabNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/high-performance-transformers-for-table","slug":"high-performance-transformers-for-table","title":"High-Performance Transformers for Table Structure Recognition Need Early Convolutions","date":"2023-11-09","arxiv_id":"2311.05565","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/high-performance-transformers-for-table#ran","syntology_url":"https://syntology.ai/paper/2311.05565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05565"}},"official":{"repos":["poloclub/tsr-convstem"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-end-to-end-multi-task-learning-model-for-1","slug":"an-end-to-end-multi-task-learning-model-for-1","title":"An End-to-End Multi-Task Learning Model for Image-based Table Recognition","date":"2023-03-15","arxiv_id":"2303.08648","repositories_listed":2,"syntology":null},{"url":"/paper/lore-logical-location-regression-network-for","slug":"lore-logical-location-regression-network-for","title":"LORE: Logical Location Regression Network for Table Structure Recognition","date":"2023-03-07","arxiv_id":"2303.03730","repositories_listed":2,"syntology":null},{"url":"/paper/scientific-evidence-extraction","slug":"scientific-evidence-extraction","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","date":"2021-09-30","arxiv_id":"2110.00061","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scientific-evidence-extraction#ran","syntology_url":"https://syntology.ai/paper/2110.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00061"}},"official":{"repos":["microsoft/table-transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lgpma-complicated-table-structure-recognition","slug":"lgpma-complicated-table-structure-recognition","title":"LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment","date":"2021-05-13","arxiv_id":"2105.06224","repositories_listed":2,"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/enhancing-table-recognition-with-vision-llms","slug":"enhancing-table-recognition-with-vision-llms","title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","date":"2024-12-30","arxiv_id":"2412.20662","repositories_listed":1,"syntology":null},{"url":"/paper/pdftable-a-unified-toolkit-for-deep-learning","slug":"pdftable-a-unified-toolkit-for-deep-learning","title":"PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction","date":"2024-09-08","arxiv_id":"2409.05125","repositories_listed":1,"syntology":null},{"url":"/paper/multi-cell-decoder-and-mutual-learning-for","slug":"multi-cell-decoder-and-mutual-learning-for","title":"Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition","date":"2024-04-20","arxiv_id":"2404.13268","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizing-realistic-data-for-table","slug":"synthesizing-realistic-data-for-table","title":"Synthesizing Realistic Data for Table Recognition","date":"2024-04-17","arxiv_id":"2404.11100","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/unitable-towards-a-unified-framework-for","slug":"unitable-towards-a-unified-framework-for","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","date":"2024-03-07","arxiv_id":"2403.04822","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unitable-towards-a-unified-framework-for#ran","syntology_url":"https://syntology.ai/paper/2403.04822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04822"}},"official":{"repos":["poloclub/unitable"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/a-large-scale-dataset-for-end-to-end-table","slug":"a-large-scale-dataset-for-end-to-end-table","title":"A large-scale dataset for end-to-end table recognition in the wild","date":"2023-03-27","arxiv_id":"2303.14884","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-image-based-table-recognition","slug":"rethinking-image-based-table-recognition","title":"Rethinking Image-based Table Recognition Using Weakly Supervised Methods","date":"2023-03-14","arxiv_id":"2303.07641","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-benchmark-datasets-for-table","slug":"aligning-benchmark-datasets-for-table","title":"Aligning benchmark datasets for table structure recognition","date":"2023-03-01","arxiv_id":"2303.00716","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/detecting-layout-templates-in-complex","slug":"detecting-layout-templates-in-complex","title":"Detecting Layout Templates in Complex Multiregion Files","date":"2021-09-14","arxiv_id":"2109.06630","repositories_listed":1,"syntology":null},{"url":"/paper/tgrnet-a-table-graph-reconstruction-network","slug":"tgrnet-a-table-graph-reconstruction-network","title":"TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition","date":"2021-06-20","arxiv_id":"2106.10598","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/tgrnet-a-table-graph-reconstruction-network#ran","syntology_url":"https://syntology.ai/paper/2106.10598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10598"}},"official":{"repos":["xuewenyuan/TGRNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tab-iais-flexible-table-recognition-and","slug":"tab-iais-flexible-table-recognition-and","title":"Flexible Table Recognition and Semantic Interpretation System","date":"2021-05-25","arxiv_id":"2105.11879","repositories_listed":1,"syntology":null},{"url":"/paper/multi-type-td-tsr-extracting-tables-from","slug":"multi-type-td-tsr-extracting-tables-from","title":"Multi-Type-TD-TSR -- Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations","date":"2021-05-23","arxiv_id":"2105.11021","repositories_listed":1,"syntology":null},{"url":"/paper/table-structure-recognition-using-top-down-1","slug":"table-structure-recognition-using-top-down-1","title":"Table Structure Recognition using Top-Down and Bottom-Up Cues","date":"2020-10-09","arxiv_id":"2010.04565","repositories_listed":1,"syntology":null},{"url":null,"slug":"benchmarking-multimodal-llms-on-recognition","title":"Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables","date":"2025-06-13","arxiv_id":"2506.11375","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-table-comprehension-in-the-wild","title":"Benchmarking Table Comprehension In The Wild","date":"2024-12-13","arxiv_id":"2412.09884","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":"vrdsynth-synthesizing-programs-for","title":"VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction","date":"2024-07-09","arxiv_id":"2407.06826","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-socface-project-large-scale-collection","title":"The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censuses","date":"2024-04-29","arxiv_id":"2404.18706","repositories_listed":0,"syntology":null},{"url":null,"slug":"tc-ocr-tablecraft-ocr-for-efficient-detection","title":"TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content","date":"2024-04-16","arxiv_id":"2404.10305","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancement-of-bengali-ocr-by-specialized","title":"Enhancement of Bengali OCR by Specialized Models and Advanced Techniques for Diverse Document Types","date":"2024-02-07","arxiv_id":"2402.05158","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-on-table-recognition-based-on-deep","title":"A Review On Table Recognition Based On Deep Learning","date":"2023-12-08","arxiv_id":"2312.04808","repositories_listed":0,"syntology":null},{"url":null,"slug":"regclr-a-self-supervised-framework-for","title":"RegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild","date":"2022-11-02","arxiv_id":"2211.01165","repositories_listed":0,"syntology":null},{"url":"/paper/trust-an-accurate-and-end-to-end-table","slug":"trust-an-accurate-and-end-to-end-table","title":"TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers","date":"2022-08-31","arxiv_id":"2208.14687","repositories_listed":0,"syntology":null},{"url":"/paper/tsrformer-table-structure-recognition-with","slug":"tsrformer-table-structure-recognition-with","title":"TSRFormer: Table Structure Recognition with Transformers","date":"2022-08-09","arxiv_id":"2208.04921","repositories_listed":0,"syntology":null},{"url":"/paper/robust-table-detection-and-structure","slug":"robust-table-detection-and-structure","title":"Robust Table Detection and Structure Recognition from Heterogeneous Document Images","date":"2022-03-17","arxiv_id":"2203.09056","repositories_listed":0,"syntology":null},{"url":"/paper/neural-collaborative-graph-machines-for-table","slug":"neural-collaborative-graph-machines-for-table","title":"Neural Collaborative Graph Machines for Table Structure Recognition","date":"2021-11-26","arxiv_id":"2111.13359","repositories_listed":0,"syntology":null},{"url":"/paper/split-embed-and-merge-an-accurate-table","slug":"split-embed-and-merge-an-accurate-table","title":"Split, embed and merge: An accurate table structure recognizer","date":"2021-07-12","arxiv_id":"2107.05214","repositories_listed":0,"syntology":null},{"url":null,"slug":"icdar-2021-competition-on-scientific-table","title":"ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX","date":"2021-05-30","arxiv_id":"2105.14426","repositories_listed":0,"syntology":null},{"url":null,"slug":"current-status-and-performance-analysis-of","title":"Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks","date":"2021-04-29","arxiv_id":"2104.14272","repositories_listed":0,"syntology":null},{"url":"/paper/guided-table-structure-recognition-through","slug":"guided-table-structure-recognition-through","title":"Guided Table Structure Recognition through Anchor Optimization","date":"2021-04-21","arxiv_id":"2104.10538","repositories_listed":0,"syntology":null},{"url":"/paper/global-table-extractor-gte-a-framework-for","slug":"global-table-extractor-gte-a-framework-for","title":"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context","date":"2020-05-01","arxiv_id":"2005.00589","repositories_listed":0,"syntology":null},{"url":null,"slug":"table-structure-recognition-based-on-cell","title":"Table Structure Recognition Based on Cell Relationship, a Bottom-Up Approach","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-machine-learning-approaches-for","title":"Comparing Machine Learning Approaches for Table Recognition in Historical Register Books","date":"2019-06-14","arxiv_id":"1906.11901","repositories_listed":0,"syntology":null},{"url":null,"slug":"ontology-driven-information-extraction","title":"Ontology-driven Information Extraction","date":"2015-12-18","arxiv_id":"1512.06034","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-table-region-in-pdf-documents-using","title":"Detecting Table Region in PDF Documents Using Distant Supervision","date":"2015-06-29","arxiv_id":"1506.08891","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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/task/table-recognition/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/table-recognition/papers/ran/1","json":"/task/table-recognition/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":"909b9e9f34257a9ad86911eb89f25d667eb1c60d416ab5c1ce9ce62f3129c874","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}