{"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":"/dataset/pubtabnet","name":"PubTabNet","full_name":"PubTabNet","description_markdown":"PubTabNet is a large dataset for image-based table recognition, containing 568k+ images of tabular data annotated with the corresponding HTML representation of the tables. The table images are extracted from the scientific publications included in the PubMed Central Open Access Subset (commercial use collection). Table regions are identified by matching the PDF format and the XML format of the articles in the PubMed Central Open Access Subset. More details are available in our paper \"Image-based table recognition: data, model, and evaluation\".","description_withheld":null,"homepage":"https://github.com/ibm-aur-nlp/PubTabNet","introduced_date":"2019-11-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/image-based-table-recognition-data-model-and","title":"Image-based table recognition: data, model, and evaluation","first_author":"Xu Zhong","url":null},"license":null,"modalities":[],"tasks":[{"name":"Table Recognition","url":"/task/table-recognition","datasets_with_task":"/datasets/task/table-recognition"}],"languages":[],"variants":["PubTabNet"],"data_loaders":[],"num_papers_in_archive":51,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/table-recognition-on-pubtabnet","task":"Table Recognition","dataset_variant":"PubTabNet","rows":13,"metrics":["TEDS (all samples)","TEDS-Struct"],"first_row_in_archive_order":{"model":"MuTabNet","paper":"/paper/multi-cell-decoder-and-mutual-learning-for","metrics":{"TEDS (all samples)":"96.87"},"code_links":[{"title":"JG1VPP/MuTabNet","url":"https://github.com/JG1VPP/MuTabNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":13,"of":13,"counts":{"papers_with_a_benchmark_row":13,"with_a_code_link":8,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":13,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/pubtabnet/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/pubtabnet/papers/ran/1","json":"/dataset/pubtabnet/papers/ran/1.json","rows":3}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":3,"samples_harvested":19,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"3da910aa893b27977036691116b105dea354f77f20cb2acabe1cd14dadec0a21","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}