{"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/rcv1","name":"RCV1","full_name":"Reuters Corpus Volume 1","description_markdown":"The **RCV1** dataset is a benchmark dataset on text categorization. It is a collection of newswire articles producd by Reuters in 1996-1997. It contains 804,414 manually labeled newswire documents, and categorized with respect to three controlled vocabularies: industries, topics and regions.\r\n\r\nSource: [Random Projections for Linear Support Vector Machines](https://arxiv.org/abs/1211.6085)\r\nImage Source: [https://www.nasdaq.com/publishers/reuters](https://www.nasdaq.com/publishers/reuters)","description_withheld":null,"homepage":"http://www.ai.mit.edu/projects/jmlr/papers/volume5/lewis04a/lyrl2004_rcv1v2_README.htm","introduced_date":"2004-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"RCV1: A New Benchmark Collection for Text Categorization Research","first_author":null,"url":"http://jmlr.org/papers/volume5/lewis04a/lewis04a.pdf"},"license":{"name":"Custom","url":"http://www.ai.mit.edu/projects/jmlr/papers/volume5/lewis04a/lyrl2004_rcv1v2_README.htm"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Multi-Label Text Classification","url":"/task/multi-label-text-classification","datasets_with_task":"/datasets/task/multi-label-text-classification"},{"name":"Hierarchical Multi-label Classification","url":"/task/hierarchical-multi-label-classification","datasets_with_task":"/datasets/task/hierarchical-multi-label-classification"},{"name":"Cross-Lingual Document Classification","url":"/task/cross-lingual-document-classification","datasets_with_task":"/datasets/task/cross-lingual-document-classification"}],"languages":[],"variants":["RCV1-v2","Reuters RCV1/RCV2 English-to-German","Reuters RCV1/RCV2 German-to-English","RCV1"],"data_loaders":[{"repo":"https://github.com/wangzemin63/dataset","url":"https://github.com/wangzemin63/dataset","frameworks":["pytorch"]}],"num_papers_in_archive":336,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hierarchical-multi-label-classification-on-17","task":"Hierarchical Multi-label Classification","dataset_variant":"RCV1-v2","rows":7,"metrics":["Macro F1","Micro F1"],"first_row_in_archive_order":{"model":"HiDEC+HBM Loss","paper":"/paper/hierarchy-aware-biased-bound-margin-loss","metrics":{"Macro F1":"71.47±0.20","Micro F1":"87.81±0.09"},"code_links":[{"title":"whitepurple/HBM-loss-for-HTC","url":"https://github.com/whitepurple/HBM-loss-for-HTC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-rcv1","task":"Text Classification","dataset_variant":"RCV1","rows":4,"metrics":["Accuracy","Macro F1","Micro F1","P@1","P@3","P@5","nDCG@1","nDCG@3","nDCG@5"],"first_row_in_archive_order":{"model":"oh-CNN + two LSTM tv-embed.","paper":"/paper/supervised-and-semi-supervised-text","metrics":{"Accuracy":"92.85"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-document-classification-on-12","task":"Cross-Lingual Document Classification","dataset_variant":"Reuters RCV1/RCV2 English-to-German","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Biinclusion (Euro500kReuters)","paper":"/paper/leveraging-monolingual-data-for-crosslingual","metrics":{"Accuracy":"92.7"},"code_links":[{"title":"ogh/binclusion","url":"https://github.com/ogh/binclusion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cross-lingual-document-classification-on-13","task":"Cross-Lingual Document Classification","dataset_variant":"Reuters RCV1/RCV2 German-to-English","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Biinclusion (Euro500kReuters)","paper":"/paper/leveraging-monolingual-data-for-crosslingual","metrics":{"Accuracy":"84.4"},"code_links":[{"title":"ogh/binclusion","url":"https://github.com/ogh/binclusion"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-label-text-classification-on-rcv1","task":"Multi-Label Text Classification","dataset_variant":"RCV1","rows":1,"metrics":["Macro-F1","Micro-F1"],"first_row_in_archive_order":{"model":"HiddeN","paper":"/paper/joint-learning-of-hyperbolic-label-embeddings","metrics":{"Macro-F1":"47.3","Micro-F1":"79.3"},"code_links":[{"title":"soumyac1999/hyperbolic-label-emb-for-hmc","url":"https://github.com/soumyac1999/hyperbolic-label-emb-for-hmc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-label-text-classification-on-rcv1-v2-1","task":"Multi-Label Text Classification","dataset_variant":"RCV1-v2","rows":1,"metrics":["Micro-F1"],"first_row_in_archive_order":{"model":"MAGNET","paper":"/paper/magnet-multi-label-text-classification-using","metrics":{"Micro-F1":"88.5"},"code_links":[{"title":"adrinta/MAGNET","url":"https://github.com/adrinta/MAGNET"},{"title":"akash18tripathi/MAGNET-Multi-Label-Text-Classi-cation-using-Attention-based-Graph-Neural-Network","url":"https://github.com/akash18tripathi/MAGNET-Multi-Label-Text-Classi-cation-using-Attention-based-Graph-Neural-Network"}]},"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":11,"of":11,"counts":{"papers_with_a_benchmark_row":11,"with_a_code_link":10,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":11,"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/hierarchy-aware-biased-bound-margin-loss","slug":"hierarchy-aware-biased-bound-margin-loss","title":"Hierarchy-aware Biased Bound Margin Loss Function for Hierarchical Text Classification","date":"2024-08-13","arxiv_id":null,"rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/hill-hierarchy-aware-information-lossless","slug":"hill-hierarchy-aware-information-lossless","title":"HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification","date":"2024-03-26","arxiv_id":"2403.17307","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["rooooyy/hill"],"state":"official (archive's flag): 3 ran","n_ran":3,"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/hill-hierarchy-aware-information-lossless#ran","syntology_url":"https://syntology.ai/paper/2403.17307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17307"}}}},{"paper":"/paper/hitin-hierarchy-aware-tree-isomorphism","slug":"hitin-hierarchy-aware-tree-isomorphism","title":"HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification","date":"2023-05-24","arxiv_id":"2305.15182","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":3,"samples_ran_checked":7,"samples_ran_instrument_failed":6,"samples_unverified":4,"pointer_only_for_licence":17,"official":{"repos":["rooooyy/hitin"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hitin-hierarchy-aware-tree-isomorphism#ran","syntology_url":"https://syntology.ai/paper/2305.15182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15182"}}}},{"paper":"/paper/joint-learning-of-hyperbolic-label-embeddings","slug":"joint-learning-of-hyperbolic-label-embeddings","title":"Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification","date":"2021-01-13","arxiv_id":"2101.04997","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/hierarchical-text-classification-with","slug":"hierarchical-text-classification-with","title":"Hierarchical Text Classification with Reinforced Label Assignment","date":"2019-08-27","arxiv_id":"1908.10419","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-scalable-and-reliable-capsule","slug":"towards-scalable-and-reliable-capsule","title":"Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications","date":"2019-06-06","arxiv_id":"1906.02829","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/supervised-and-semi-supervised-text","slug":"supervised-and-semi-supervised-text","title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","date":"2016-02-07","arxiv_id":"1602.02373","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/leveraging-monolingual-data-for-crosslingual","slug":"leveraging-monolingual-data-for-crosslingual","title":"Leveraging Monolingual Data for Crosslingual Compositional Word Representations","date":"2014-12-19","arxiv_id":"1412.6334","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multilingual-models-for-compositional","slug":"multilingual-models-for-compositional","title":"Multilingual Models for Compositional Distributed Semantics","date":"2014-04-17","arxiv_id":"1404.4641","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multilingual-distributed-representations","slug":"multilingual-distributed-representations","title":"Multilingual Distributed Representations without Word Alignment","date":"2013-12-20","arxiv_id":"1312.6173","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/hierarchy-aware-biased-bound-margin-loss","slug":"hierarchy-aware-biased-bound-margin-loss","title":"Hierarchy-aware Biased Bound Margin Loss Function for Hierarchical Text Classification","date":"2024-08-13","arxiv_id":null,"rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/hill-hierarchy-aware-information-lossless","slug":"hill-hierarchy-aware-information-lossless","title":"HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification","date":"2024-03-26","arxiv_id":"2403.17307","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["rooooyy/hill"],"state":"official (archive's flag): 3 ran","n_ran":3,"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/hill-hierarchy-aware-information-lossless#ran","syntology_url":"https://syntology.ai/paper/2403.17307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17307"}}}},{"paper":"/paper/hitin-hierarchy-aware-tree-isomorphism","slug":"hitin-hierarchy-aware-tree-isomorphism","title":"HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification","date":"2023-05-24","arxiv_id":"2305.15182","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":13,"samples_constructed":3,"samples_ran_checked":7,"samples_ran_instrument_failed":6,"samples_unverified":4,"pointer_only_for_licence":17,"official":{"repos":["rooooyy/hitin"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hitin-hierarchy-aware-tree-isomorphism#ran","syntology_url":"https://syntology.ai/paper/2305.15182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15182"}}}},{"paper":"/paper/joint-learning-of-hyperbolic-label-embeddings","slug":"joint-learning-of-hyperbolic-label-embeddings","title":"Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification","date":"2021-01-13","arxiv_id":"2101.04997","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/hierarchical-text-classification-with","slug":"hierarchical-text-classification-with","title":"Hierarchical Text Classification with Reinforced Label Assignment","date":"2019-08-27","arxiv_id":"1908.10419","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-scalable-and-reliable-capsule","slug":"towards-scalable-and-reliable-capsule","title":"Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications","date":"2019-06-06","arxiv_id":"1906.02829","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/supervised-and-semi-supervised-text","slug":"supervised-and-semi-supervised-text","title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","date":"2016-02-07","arxiv_id":"1602.02373","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/leveraging-monolingual-data-for-crosslingual","slug":"leveraging-monolingual-data-for-crosslingual","title":"Leveraging Monolingual Data for Crosslingual Compositional Word Representations","date":"2014-12-19","arxiv_id":"1412.6334","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multilingual-models-for-compositional","slug":"multilingual-models-for-compositional","title":"Multilingual Models for Compositional Distributed Semantics","date":"2014-04-17","arxiv_id":"1404.4641","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multilingual-distributed-representations","slug":"multilingual-distributed-representations","title":"Multilingual Distributed Representations without Word Alignment","date":"2013-12-20","arxiv_id":"1312.6173","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/rcv1/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/rcv1/papers/ran/1","json":"/dataset/rcv1/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":20,"samples_ran":16,"samples_constructed":3,"samples_ran_checked":8,"samples_ran_instrument_failed":8,"samples_unverified":4,"pointer_only_for_licence":19,"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":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/hierarchical-multi-label-classification-on-17","since_archive":"/sota/hierarchical-multi-label-classification-on-17#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/multi-label-text-classification-on-rcv1-v2-1","since_archive":"/sota/multi-label-text-classification-on-rcv1-v2-1#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":"2ef9d3f63fb816b840b4c004c6076a08e2ef9826dc919a0efccef9e9fed3b5e8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}