{"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/wikibio","name":"WikiBio","full_name":"Wikipedia Biography Dataset","description_markdown":"This dataset gathers 728,321 biographies from English Wikipedia. It aims at evaluating text generation algorithms. For each article, we provide the first paragraph and the infobox (both tokenized).","description_withheld":null,"homepage":"https://rlebret.github.io/wikipedia-biography-dataset/","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/neural-text-generation-from-structured-data","title":"Neural Text Generation from Structured Data with Application to the Biography Domain","first_author":"Remi Lebret","url":null},"license":{"name":"CC BY-SA 3.0","url":"https://github.com/rlebret/wikipedia-biography-dataset/blob/master/LICENSE.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Table-to-Text Generation","url":"/task/table-to-text-generation","datasets_with_task":"/datasets/task/table-to-text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiBio"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/michaelauli/wiki_bio","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki_bio","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/wiki_bio","frameworks":["tf","jax"]}],"num_papers_in_archive":84,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/table-to-text-generation-on-wikibio","task":"Table-to-Text Generation","dataset_variant":"WikiBio","rows":4,"metrics":["BLEU","ROUGE","PARENT"],"first_row_in_archive_order":{"model":"Field-gating Seq2seq + dual attention","paper":"/paper/table-to-text-generation-by-structure-aware","metrics":{"BLEU":"44.89","ROUGE":"41.21"},"code_links":[{"title":"tyliupku/wiki2bio","url":"https://github.com/tyliupku/wiki2bio"},{"title":"anjbapat/D2T","url":"https://github.com/anjbapat/D2T"},{"title":"Parth27/Data2Text","url":"https://github.com/Parth27/Data2Text"}]},"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":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":3,"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/controlling-hallucinations-at-word-level-in","slug":"controlling-hallucinations-at-word-level-in","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","date":"2021-02-04","arxiv_id":"2102.02810","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/table-to-text-generation-by-structure-aware","slug":"table-to-text-generation-by-structure-aware","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","date":"2017-11-27","arxiv_id":"1711.09724","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/neural-text-generation-from-structured-data","slug":"neural-text-generation-from-structured-data","title":"Neural Text Generation from Structured Data with Application to the Biography Domain","date":"2016-03-24","arxiv_id":"1603.07771","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/controlling-hallucinations-at-word-level-in","slug":"controlling-hallucinations-at-word-level-in","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","date":"2021-02-04","arxiv_id":"2102.02810","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/table-to-text-generation-by-structure-aware","slug":"table-to-text-generation-by-structure-aware","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","date":"2017-11-27","arxiv_id":"1711.09724","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/neural-text-generation-from-structured-data","slug":"neural-text-generation-from-structured-data","title":"Neural Text Generation from Structured Data with Application to the Biography Domain","date":"2016-03-24","arxiv_id":"1603.07771","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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/table-to-text-generation-on-wikibio","since_archive":"/sota/table-to-text-generation-on-wikibio#since-judged","papers_judged":1,"placed":0}]},"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":"a77d6223bb8932b22382744ff6744f1549ef7926a89c37ade307f0b73ebef905","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}