{"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/ws353","name":"WS353","full_name":"WordSim-353","description_markdown":"Lev Finkelstein, Evgeniy Gabrilovich, Yossi Matias, Ehud Rivlin, Zach Solan, Gadi Wolfman, and Ey\u0002tan Ruppin. 2001. Placing search in context: The concept revisited. In Proceedings of the 10th in\u0002ternational conference on World Wide Web, pages 406–414","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Word Similarity","url":"/task/word-similarity","datasets_with_task":"/datasets/task/word-similarity"}],"languages":[],"variants":["WS353"],"data_loaders":[{"repo":"https://github.com/facebookresearch/fastText","url":"https://github.com/facebookresearch/fastText","frameworks":["pytorch"]},{"repo":"https://github.com/binbinjiang/context2vector","url":"https://github.com/binbinjiang/context2vector","frameworks":["pytorch"]},{"repo":"https://github.com/ylwangy/bert2vec","url":"https://github.com/ylwangy/bert2vec","frameworks":[]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/word-similarity-on-ws353","task":"Word Similarity","dataset_variant":"WS353","rows":3,"metrics":["Spearman's Rho"],"first_row_in_archive_order":{"model":"Context-to-Vector","paper":"/paper/using-context-to-vector-with-graph-1","metrics":{"Spearman's Rho":"78.9"},"code_links":[{"title":"binbinjiang/context2vector","url":"https://github.com/binbinjiang/context2vector"}]},"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":2,"not_listed_spam_title":0,"listed":3,"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/using-context-to-vector-with-graph-1","slug":"using-context-to-vector-with-graph-1","title":"Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings","date":"2022-10-30","arxiv_id":"2210.16848","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["binbinjiang/context2vector"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/using-context-to-vector-with-graph-1#ran","syntology_url":"https://syntology.ai/paper/2210.16848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16848"}}}},{"paper":"/paper/improved-biomedical-word-embeddings-in-the","slug":"improved-biomedical-word-embeddings-in-the","title":"Improved Biomedical Word Embeddings in the Transformer Era","date":"2020-12-22","arxiv_id":"2012.11808","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enriching-word-vectors-with-subword","slug":"enriching-word-vectors-with-subword","title":"Enriching Word Vectors with Subword Information","date":"2016-07-15","arxiv_id":"1607.04606","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":21,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/fastText"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/enriching-word-vectors-with-subword#ran","syntology_url":"https://syntology.ai/paper/1607.04606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.04606"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/using-context-to-vector-with-graph-1","slug":"using-context-to-vector-with-graph-1","title":"Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings","date":"2022-10-30","arxiv_id":"2210.16848","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["binbinjiang/context2vector"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/using-context-to-vector-with-graph-1#ran","syntology_url":"https://syntology.ai/paper/2210.16848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16848"}}}},{"paper":"/paper/improved-biomedical-word-embeddings-in-the","slug":"improved-biomedical-word-embeddings-in-the","title":"Improved Biomedical Word Embeddings in the Transformer Era","date":"2020-12-22","arxiv_id":"2012.11808","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enriching-word-vectors-with-subword","slug":"enriching-word-vectors-with-subword","title":"Enriching Word Vectors with Subword Information","date":"2016-07-15","arxiv_id":"1607.04606","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":21,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/fastText"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/enriching-word-vectors-with-subword#ran","syntology_url":"https://syntology.ai/paper/1607.04606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.04606"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/ws353/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/ws353/papers/ran/1","json":"/dataset/ws353/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":33,"samples_ran":26,"samples_constructed":1,"samples_ran_checked":22,"samples_ran_instrument_failed":4,"samples_unverified":7,"pointer_only_for_licence":6,"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":"4581ab812978a16975b10ff93e9ea7f07c4b1ca9219ba78104e5625cc4f06175","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}