{"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/20-newsgroups","name":"20 Newsgroups","full_name":null,"description_markdown":"The 20 Newsgroups data set is a collection of approximately 20,000 newsgroup documents, partitioned (nearly) evenly across 20 different newsgroups.","description_withheld":null,"homepage":"http://qwone.com/~jason/20Newsgroups/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Out-of-Distribution Detection","url":"/task/out-of-distribution-detection","datasets_with_task":"/datasets/task/out-of-distribution-detection"},{"name":"Text Clustering","url":"/task/text-clustering","datasets_with_task":"/datasets/task/text-clustering"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Topic Models","url":"/task/topic-models","datasets_with_task":"/datasets/task/topic-models"},{"name":"Supervised Text Retrieval","url":"/task/supervised-text-retrieval","datasets_with_task":"/datasets/task/supervised-text-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["20 Newsgroups"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/newsgroup","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/newsgroup","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/graviti/Newsgroups20","frameworks":["tf","pytorch"]}],"num_papers_in_archive":27,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-retrieval-on-20-newsgroups","task":"Text Retrieval","dataset_variant":"20 Newsgroups","rows":3,"metrics":["Precision@100"],"first_row_in_archive_order":{"model":"B-VAE","paper":"/paper/a-binary-variational-autoencoder-for-hashing","metrics":{"Precision@100":"0.441"},"code_links":[{"title":"fmenat/DiscreteVAE","url":"https://github.com/fmenat/DiscreteVAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/out-of-distribution-detection-on-20","task":"Out-of-Distribution Detection","dataset_variant":"20 Newsgroups","rows":2,"metrics":["AUROC","FPR95"],"first_row_in_archive_order":{"model":"2-Layered GRU","paper":"/paper/an-effective-baseline-for-robustness-to","metrics":{"AUROC":"99.6","FPR95":"1.78"},"code_links":[{"title":"Sushil-Thapa/Abstention-OoD","url":"https://github.com/Sushil-Thapa/Abstention-OoD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-clustering-on-20-newsgroups","task":"Text Clustering","dataset_variant":"20 Newsgroups","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"G-BAT","paper":"/paper/neural-topic-modeling-with-bidirectional","metrics":{"Accuracy":"41.25"},"code_links":[{"title":"zll17/Neural_Topic_Models","url":"https://github.com/zll17/Neural_Topic_Models"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/topic-models-on-20-newsgroups","task":"Topic Models","dataset_variant":"20 Newsgroups","rows":2,"metrics":["Test perplexity"],"first_row_in_archive_order":{"model":"Bayesian SMM","paper":"/paper/190807599","metrics":{"Test perplexity":"515"},"code_links":[{"title":"skesiraju/BaySMM","url":"https://github.com/skesiraju/BaySMM"},{"title":"BUTSpeechFIT/BaySMM","url":"https://github.com/BUTSpeechFIT/BaySMM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-20-newsgroups","task":"Text Classification","dataset_variant":"20 Newsgroups","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RoBERTaGCN","paper":"/paper/bertgcn-transductive-text-classification-by","metrics":{"Accuracy":"89.5"},"code_links":[{"title":"ZeroRin/BertGCN","url":"https://github.com/ZeroRin/BertGCN"}]},"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":8,"of":8,"counts":{"papers_with_a_benchmark_row":8,"with_a_code_link":8,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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/an-effective-baseline-for-robustness-to","slug":"an-effective-baseline-for-robustness-to","title":"An Effective Baseline for Robustness to Distributional Shift","date":"2021-05-15","arxiv_id":"2105.07107","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bertgcn-transductive-text-classification-by","slug":"bertgcn-transductive-text-classification-by","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","date":"2021-05-12","arxiv_id":"2105.05727","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-topic-modeling-with-bidirectional","slug":"neural-topic-modeling-with-bidirectional","title":"Neural Topic Modeling with Bidirectional Adversarial Training","date":"2020-04-26","arxiv_id":"2004.12331","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-binary-variational-autoencoder-for-hashing","slug":"a-binary-variational-autoencoder-for-hashing","title":"A Binary Variational Autoencoder for Hashing","date":"2019-10-22","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/190807599","slug":"190807599","title":"Learning document embeddings along with their uncertainties","date":"2019-08-20","arxiv_id":"1908.07599","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/simultaneous-classification-and-novelty","slug":"simultaneous-classification-and-novelty","title":"Outlier Exposure with Confidence Control for Out-of-Distribution Detection","date":"2019-06-08","arxiv_id":"1906.03509","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/variational-deep-semantic-hashing-for-text","slug":"variational-deep-semantic-hashing-for-text","title":"Variational Deep Semantic Hashing for Text Documents","date":"2017-08-11","arxiv_id":"1708.03436","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-variational-inference-for-text","slug":"neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","arxiv_id":"1511.06038","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-variational-inference-for-text#ran","syntology_url":"https://syntology.ai/paper/1511.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06038"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/an-effective-baseline-for-robustness-to","slug":"an-effective-baseline-for-robustness-to","title":"An Effective Baseline for Robustness to Distributional Shift","date":"2021-05-15","arxiv_id":"2105.07107","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bertgcn-transductive-text-classification-by","slug":"bertgcn-transductive-text-classification-by","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","date":"2021-05-12","arxiv_id":"2105.05727","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-topic-modeling-with-bidirectional","slug":"neural-topic-modeling-with-bidirectional","title":"Neural Topic Modeling with Bidirectional Adversarial Training","date":"2020-04-26","arxiv_id":"2004.12331","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-binary-variational-autoencoder-for-hashing","slug":"a-binary-variational-autoencoder-for-hashing","title":"A Binary Variational Autoencoder for Hashing","date":"2019-10-22","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/190807599","slug":"190807599","title":"Learning document embeddings along with their uncertainties","date":"2019-08-20","arxiv_id":"1908.07599","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/simultaneous-classification-and-novelty","slug":"simultaneous-classification-and-novelty","title":"Outlier Exposure with Confidence Control for Out-of-Distribution Detection","date":"2019-06-08","arxiv_id":"1906.03509","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/variational-deep-semantic-hashing-for-text","slug":"variational-deep-semantic-hashing-for-text","title":"Variational Deep Semantic Hashing for Text Documents","date":"2017-08-11","arxiv_id":"1708.03436","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-variational-inference-for-text","slug":"neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","arxiv_id":"1511.06038","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-variational-inference-for-text#ran","syntology_url":"https://syntology.ai/paper/1511.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06038"}}}}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/20-newsgroups/papers/ran/1","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":[{"order":"ran","page":1,"of":1,"url":"/dataset/20-newsgroups/papers/ran/1","json":"/dataset/20-newsgroups/papers/ran/1.json","rows":1}],"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":1,"samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"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":"f867fa1b61333e84a5e05ace51e96db0ff22c74386ae8a22e42b82e7d6497462","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}