{"url":"/sota/extractive-text-summarization-on-govreport","task":{"name":"Extractive Text Summarization","url":"/task/extractive-document-summarization","note":null},"dataset":{"name":"GovReport","url":"/dataset/govreport"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Given a document, selecting a subset of the words or sentences which best represents a summary of the document.","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":["Avg. Test Rouge1","Avg. Test Rouge2","Avg. Test RougeLsum"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Avg. Test Rouge1":null,"Avg. Test Rouge2":null,"Avg. Test RougeLsum":null}},"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":"MemSum (extractive)","metrics":{"Avg. Test Rouge1":"59.43","Avg. Test Rouge2":"28.60","Avg. Test RougeLsum":"56.69"},"uses_additional_data":false,"paper_date":"2021-07-19","paper":"/paper/memsum-extractive-summarization-of-long","paper_url":"https://arxiv.org/abs/2107.08929v2","paper_title":"MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes","code":"https://github.com/nianlonggu/memsum","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"HEPOS","metrics":{"Avg. Test Rouge1":"56.86","Avg. Test Rouge2":"22.62","Avg. Test RougeLsum":"53.82"},"uses_additional_data":false,"paper_date":"2018-12-04","paper":"/paper/factorized-attention-self-attention-with","paper_url":"https://arxiv.org/abs/1812.01243v9","paper_title":"Efficient Attention: Attention with Linear Complexities","code":"https://github.com/lucidrains/DALLE2-pytorch","n_code_links":14,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":1}}],"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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":1,"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"}}}