{"url":"/sota/table-recognition-on-wtw","task":{"name":"Table Recognition","url":"/task/table-recognition","note":null},"dataset":{"name":"WTW","url":"/dataset/wtw"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher"}},"counts":{"rows":1,"rows_with_code":1,"rows_with_paper_page":1,"rows_dated":1,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"StrucTexTv2 (small)","metrics":{"F1":"78.9%"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/structextv2-masked-visual-textual-prediction","paper_url":"https://arxiv.org/abs/2303.00289v1","paper_title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","code":"https://github.com/PaddlePaddle/VIMER/tree/main/StrucTexT/v2","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}