{"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/rutermeval-track-2","name":"RuTermEval (Track 2)","full_name":"CL-RuTerm3","description_markdown":"CL-RuTerm3 dataset is a novel resource featuring nested term annotations across six domains (the main one is computational linguistics, also mathematics, medicine, economics, literature studies, and agrochemistry), and the RuTermEval-2024 competition, designed to evaluate term extraction systems on this data. The CL-RuTerm3 dataset, comprising 1270 abstracts and 15 full-text articles (over 165k tokens with over 37k annotated entities), is the largest of its kind for Russian scientific texts. Terms are classified into three categories based on lexical and domain specificity: specific terms, common terms, and nomens. The dataset’s unique features, such as nested term markup and cross-domain coverage, enable more realistic evaluation of ATE systems. \r\n\r\nSecond track is devoted to Nested term extraction (in sequence labeling format) and classification (labels are specific, common, nomen).","description_withheld":null,"homepage":"https://dialogue-conf.org/wp-content/uploads/2025/04/MamontovaAIschenkoRVorontsovK.pdf","introduced_date":"2025-04-23","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Term Extraction","url":"/task/term-extraction","datasets_with_task":"/datasets/task/term-extraction"},{"name":"Nested Named Entity Recognition","url":"/task/nested-named-entity-recognition","datasets_with_task":"/datasets/task/nested-named-entity-recognition"},{"name":"Nested Term Extraction","url":"/task/nested-term-extraction","datasets_with_task":"/datasets/task/nested-term-extraction"},{"name":"Nested Term Recognition from Flat Supervision","url":"/task/nested-term-recognition-from-flat-supervision","datasets_with_task":"/datasets/task/nested-term-recognition-from-flat-supervision"}],"languages":[{"name":"Russian","url":"/datasets/language/russian"}],"variants":["RuTermEval (Track 2)"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/nested-term-extraction-on-rutermeval-track-2","task":"Nested Term Extraction","dataset_variant":"RuTermEval (Track 2)","rows":1,"metrics":["Scoreboard Class-agnostic F1","Scoreboard Weighted F1"],"first_row_in_archive_order":{"model":"full nested","paper":"/paper/methods-for-recognizing-nested-terms","metrics":{"Scoreboard Class-agnostic F1":"0.78","Scoreboard Weighted F1":"0.6997"},"code_links":[{"title":"fulstock/Methods-for-Recognizing-Nested-Terms","url":"https://github.com/fulstock/Methods-for-Recognizing-Nested-Terms"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/nested-term-recognition-from-flat-supervision-1","task":"Nested Term Recognition from Flat Supervision","dataset_variant":"RuTermEval (Track 2)","rows":1,"metrics":["Scoreboard Class-agnostic F1","Scoreboard Weighted F1"],"first_row_in_archive_order":{"model":"lemm. inc. + early dmg","paper":"/paper/methods-for-recognizing-nested-terms","metrics":{"Scoreboard Class-agnostic F1":"0.7337","Scoreboard Weighted F1":"0.631"},"code_links":[{"title":"fulstock/Methods-for-Recognizing-Nested-Terms","url":"https://github.com/fulstock/Methods-for-Recognizing-Nested-Terms"}]},"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":1,"of":1,"counts":{"papers_with_a_benchmark_row":1,"with_a_code_link":1,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":1,"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/methods-for-recognizing-nested-terms","slug":"methods-for-recognizing-nested-terms","title":"Methods for Recognizing Nested Terms","date":"2025-04-22","arxiv_id":"2504.16007","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/methods-for-recognizing-nested-terms","slug":"methods-for-recognizing-nested-terms","title":"Methods for Recognizing Nested Terms","date":"2025-04-22","arxiv_id":"2504.16007","rows_on_this_dataset":2,"code_links":1,"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":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":"01a3ba028ceccae7a4065d9e603da439bbd008b8d9088dcb7fa7e63cfb3687f3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}