{"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/reuters-21578","name":"Reuters-21578","full_name":null,"description_markdown":"The **Reuters-21578** dataset is a collection of documents with news articles. The original corpus has 10,369 documents and a vocabulary of 29,930 words.\r\n\r\nSource: [Topic Model Based Multi-Label Classification from the Crowd](https://arxiv.org/abs/1604.00783)","description_withheld":null,"homepage":"http://kdd.ics.uci.edu/databases/reuters21578/reuters21578.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"Reuters-21578","first_author":null,"url":"http://www.daviddlewis.com/resources/testcollections/reuters21578"},"license":{"name":"Custom (research-only, attribution)","url":"http://kdd.ics.uci.edu/databases/reuters21578/README.txt"},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Unsupervised Anomaly Detection","url":"/task/unsupervised-anomaly-detection","datasets_with_task":"/datasets/task/unsupervised-anomaly-detection"},{"name":"Document Classification","url":"/task/document-classification","datasets_with_task":"/datasets/task/document-classification"},{"name":"Multi-Label Text Classification","url":"/task/multi-label-text-classification","datasets_with_task":"/datasets/task/multi-label-text-classification"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Multi-Modal Document Classification","url":"/task/multi-modal-document-classification","datasets_with_task":"/datasets/task/multi-modal-document-classification"},{"name":"Supervised Text Retrieval","url":"/task/supervised-text-retrieval","datasets_with_task":"/datasets/task/supervised-text-retrieval"}],"languages":[],"variants":["Reuters-21578","reuters21578"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/ucirvine/reuters21578","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/reuters21578","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":66,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-classification-on-reuters-21578","task":"Document Classification","dataset_variant":"Reuters-21578","rows":8,"metrics":["Accuracy","F1"],"first_row_in_archive_order":{"model":"ApproxRepSet","paper":"/paper/rep-the-set-neural-networks-for-learning-set","metrics":{"Accuracy":"97.17"},"code_links":[{"title":"giannisnik/repset","url":"https://github.com/giannisnik/repset"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-label-text-classification-on-reuters-1","task":"Multi-Label Text Classification","dataset_variant":"Reuters-21578","rows":7,"metrics":["Micro-F1"],"first_row_in_archive_order":{"model":"TIACBM","paper":"/paper/task-informed-anti-curriculum-by-masking","metrics":{"Micro-F1":"91.2±0.20"},"code_links":[{"title":"jarcaandrei/tiacbm","url":"https://github.com/jarcaandrei/tiacbm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-retrieval-on-reuters-21578","task":"Text Retrieval","dataset_variant":"Reuters-21578","rows":3,"metrics":["Precision@100"],"first_row_in_archive_order":{"model":"VDSH","paper":"/paper/variational-deep-semantic-hashing-for-text","metrics":{"Precision@100":"0.7753"},"code_links":[{"title":"unsuthee/VariationalDeepSemanticHashing","url":"https://github.com/unsuthee/VariationalDeepSemanticHashing"},{"title":"J-zin/SNUH","url":"https://github.com/J-zin/SNUH"},{"title":"MindSpore-scientific/code-9","url":"https://github.com/MindSpore-scientific/code-9/tree/main/SNUH"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-anomaly-detection-on-reuters-1","task":"Unsupervised Anomaly Detection","dataset_variant":"Reuters-21578","rows":1,"metrics":["AUC (outlier ratio = 0.5)"],"first_row_in_archive_order":{"model":"RSRAE","paper":"/paper/robust-subspace-recovery-layer-for","metrics":{"AUC (outlier ratio = 0.5)":"0.849"},"code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-reuters21578","task":"Text Classification","dataset_variant":"reuters21578","rows":0,"metrics":["Accuracy","F1"],"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":14,"of":14,"counts":{"papers_with_a_benchmark_row":14,"with_a_code_link":14,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"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/task-informed-anti-curriculum-by-masking","slug":"task-informed-anti-curriculum-by-masking","title":"Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text","date":"2025-02-18","arxiv_id":"2502.12953","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/co-attention-network-with-label-embedding-for","slug":"co-attention-network-with-label-embedding-for","title":"Co-attention network with label embedding for text classification","date":"2021-11-04","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/balancing-methods-for-multi-label-text","slug":"balancing-methods-for-multi-label-text","title":"Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution","date":"2021-09-10","arxiv_id":"2109.04712","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/text-classification-with-word-embedding","slug":"text-classification-with-word-embedding","title":"Text classification with word embedding regularization and soft similarity measure","date":"2020-03-10","arxiv_id":"2003.05019","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/magnet-multi-label-text-classification-using","slug":"magnet-multi-label-text-classification-using","title":"MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network","date":"2020-02-24","arxiv_id":null,"rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/speeding-up-word-movers-distance-and-its","slug":"speeding-up-word-movers-distance-and-its","title":"Speeding up Word Mover's Distance and its variants via properties of distances between embeddings","date":"2019-12-01","arxiv_id":"1912.00509","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["matwerner/fast-wmd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/speeding-up-word-movers-distance-and-its#ran","syntology_url":"https://syntology.ai/paper/1912.00509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00509"}}}},{"paper":"/paper/improving-document-classification-with-multi","slug":"improving-document-classification-with-multi","title":"Improving Document Classification with Multi-Sense Embeddings","date":"2019-11-18","arxiv_id":"1911.07918","rows_on_this_dataset":1,"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/rethinking-complex-neural-network","slug":"rethinking-complex-neural-network","title":"Rethinking Complex Neural Network Architectures for Document Classification","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/docbert-bert-for-document-classification","slug":"docbert-bert-for-document-classification","title":"DocBERT: BERT for Document Classification","date":"2019-04-17","arxiv_id":"1904.08398","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["castorini/hedwig"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/docbert-bert-for-document-classification#ran","syntology_url":"https://syntology.ai/paper/1904.08398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08398"}}}},{"paper":"/paper/rep-the-set-neural-networks-for-learning-set","slug":"rep-the-set-neural-networks-for-learning-set","title":"Rep the Set: Neural Networks for Learning Set Representations","date":"2019-04-03","arxiv_id":"1904.01962","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/robust-subspace-recovery-layer-for","slug":"robust-subspace-recovery-layer-for","title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","date":"2019-03-30","arxiv_id":"1904.00152","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/vector-of-locally-aggregated-word-embeddings","slug":"vector-of-locally-aggregated-word-embeddings","title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation","date":"2019-02-23","arxiv_id":"1902.08850","rows_on_this_dataset":2,"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}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/task-informed-anti-curriculum-by-masking","slug":"task-informed-anti-curriculum-by-masking","title":"Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text","date":"2025-02-18","arxiv_id":"2502.12953","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/co-attention-network-with-label-embedding-for","slug":"co-attention-network-with-label-embedding-for","title":"Co-attention network with label embedding for text classification","date":"2021-11-04","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/balancing-methods-for-multi-label-text","slug":"balancing-methods-for-multi-label-text","title":"Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution","date":"2021-09-10","arxiv_id":"2109.04712","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/text-classification-with-word-embedding","slug":"text-classification-with-word-embedding","title":"Text classification with word embedding regularization and soft similarity measure","date":"2020-03-10","arxiv_id":"2003.05019","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/magnet-multi-label-text-classification-using","slug":"magnet-multi-label-text-classification-using","title":"MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network","date":"2020-02-24","arxiv_id":null,"rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/speeding-up-word-movers-distance-and-its","slug":"speeding-up-word-movers-distance-and-its","title":"Speeding up Word Mover's Distance and its variants via properties of distances between embeddings","date":"2019-12-01","arxiv_id":"1912.00509","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["matwerner/fast-wmd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/speeding-up-word-movers-distance-and-its#ran","syntology_url":"https://syntology.ai/paper/1912.00509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00509"}}}},{"paper":"/paper/improving-document-classification-with-multi","slug":"improving-document-classification-with-multi","title":"Improving Document Classification with Multi-Sense Embeddings","date":"2019-11-18","arxiv_id":"1911.07918","rows_on_this_dataset":1,"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/rethinking-complex-neural-network","slug":"rethinking-complex-neural-network","title":"Rethinking Complex Neural Network Architectures for Document Classification","date":"2019-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/docbert-bert-for-document-classification","slug":"docbert-bert-for-document-classification","title":"DocBERT: BERT for Document Classification","date":"2019-04-17","arxiv_id":"1904.08398","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["castorini/hedwig"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/docbert-bert-for-document-classification#ran","syntology_url":"https://syntology.ai/paper/1904.08398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08398"}}}},{"paper":"/paper/rep-the-set-neural-networks-for-learning-set","slug":"rep-the-set-neural-networks-for-learning-set","title":"Rep the Set: Neural Networks for Learning Set Representations","date":"2019-04-03","arxiv_id":"1904.01962","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/robust-subspace-recovery-layer-for","slug":"robust-subspace-recovery-layer-for","title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","date":"2019-03-30","arxiv_id":"1904.00152","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/vector-of-locally-aggregated-word-embeddings","slug":"vector-of-locally-aggregated-word-embeddings","title":"Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation","date":"2019-02-23","arxiv_id":"1902.08850","rows_on_this_dataset":2,"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}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/reuters-21578/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/reuters-21578/papers/ran/1","json":"/dataset/reuters-21578/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":15,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"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":"708837288d57836dd574e114bddb6d02392345b8597f18b8f9c5b4b48b2e9e2c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}