{"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/billsum","name":"BillSum","full_name":"BillSum","description_markdown":"BillSum is the first dataset for summarization of US Congressional and California state bills.\r\n\r\nThe BillSum dataset consists of three parts: US training bills, US test bills and California test bills. The US bills were collected from the Govinfo service provided by the United States Government Publishing Office (GPO). The corpus consists of bills from the 103rd-115th (1993-2018) sessions of Congress. The data was split into 18,949 train bills and 3,269 test bills. For California, bills from the 2015-2016 session were scraped directly from the legislature’s website; the summaries were written by their Legislative Counsel.\r\n\r\nThe BillSum corpus focuses on mid-length legislation from 5,000 to 20,000 character in length. The authors chose to measure the text length in characters, instead of words or sentences, because the texts have complex structure that makes it difficult to consistently measure words. The range was chosen because on one side, short bills introduce minor changes and do not require summaries. While the CRS produces summaries for them, they often contain most of the text of the bill. On the\r\nother side, very long legislation is often composed of several large sections.\r\n\r\nSource: [BillSum: A Corpus for Automatic Summarization of US Legislation](https://arxiv.org/pdf/1910.00523v2.pdf)","description_withheld":null,"homepage":"https://github.com/FiscalNote/BillSum","introduced_date":"2019-10-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/billsum-a-corpus-for-automatic-summarization","title":"BillSum: A Corpus for Automatic Summarization of US Legislation","first_author":"Anastassia Kornilova","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"},{"name":"Sequence-to-sequence Language Modeling","url":"/task/sequence-to-sequence-language-modeling","datasets_with_task":"/datasets/task/sequence-to-sequence-language-modeling"},{"name":"Summarization","url":"/task/summarization","datasets_with_task":"/datasets/task/summarization"},{"name":"Point Processes","url":"/task/point-processes","datasets_with_task":"/datasets/task/point-processes"},{"name":"Legal Document Summarization","url":"/task/legal-document-summarization","datasets_with_task":"/datasets/task/legal-document-summarization"}],"languages":[],"variants":["BillSum"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/FiscalNote/billsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/billsum","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/billsum","frameworks":["tf","jax"]},{"repo":"https://github.com/FiscalNote/BillSum","url":"https://github.com/FiscalNote/BillSum","frameworks":["tf"]}],"num_papers_in_archive":47,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-billsum","task":"Text Summarization","dataset_variant":"BillSum","rows":1,"metrics":["rouge1"],"first_row_in_archive_order":{"model":"Longformer Encoder Decoder","paper":"/paper/billsum-a-corpus-for-automatic-summarization","metrics":{"rouge1":"38.650"},"code_links":[{"title":"FiscalNote/BillSum","url":"https://github.com/FiscalNote/BillSum"},{"title":"allisontam/bills867","url":"https://github.com/allisontam/bills867"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/summarization-on-billsum","task":"Summarization","dataset_variant":"BillSum","rows":0,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L","ROUGE-LSUM","gen_len","loss"],"first_row_in_archive_order":null,"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":1,"of":1,"counts":{"papers_with_a_benchmark_row":1,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":1,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"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/billsum-a-corpus-for-automatic-summarization","slug":"billsum-a-corpus-for-automatic-summarization","title":"BillSum: A Corpus for Automatic Summarization of US Legislation","date":"2019-10-01","arxiv_id":"1910.00523","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/billsum-a-corpus-for-automatic-summarization","slug":"billsum-a-corpus-for-automatic-summarization","title":"BillSum: A Corpus for Automatic Summarization of US Legislation","date":"2019-10-01","arxiv_id":"1910.00523","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"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":[],"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":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"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":"d4fbd78faad235b8e202bd110845b14e889084c2eddb83e1536bcdd0d5449ef3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}