{"url":"/sota/attribute-extraction-on-swde","task":{"name":"Attribute Extraction","url":"/task/attribute-extraction","note":null},"dataset":{"name":"SWDE","url":"/dataset/swde"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":null,"description_from":null,"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":["Avg F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Avg F1":"higher"}},"counts":{"rows":2,"rows_with_code":2,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"InstrucTE (zero-shot)","metrics":{"Avg F1":"95.7"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/schema-driven-information-extraction-from","paper_url":"https://arxiv.org/abs/2305.14336v5","paper_title":"Schema-Driven Information Extraction from Heterogeneous Tables","code":"https://github.com/bflashcp3f/schema-to-json","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DOM-LM","metrics":{"Avg F1":"94.2"},"uses_additional_data":false,"paper_date":"2022-01-25","paper":"/paper/dom-lm-learning-generalizable-representations","paper_url":"https://arxiv.org/abs/2201.10608v1","paper_title":"DOM-LM: Learning Generalizable Representations for HTML Documents","code":"https://github.com/Misterion777/DOM-LM","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"}}}