{"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/gum","name":"GUM","full_name":"Georgetown University Multilayer corpus","description_markdown":"GUM is an open source multilayer English corpus of richly annotated texts from twelve text types. Annotations include:\r\n\r\n  * Multiple POS tags, morphological features and lemmatization\r\n  * Sentence segmentation and rough speech act\r\n  * Document structure in TEI XML (paragraphs, headings, figures, etc.)\r\n  * ISO date/time annotations\r\n  * Speaker and addressee information (where relevant)\r\n  * Constituent and dependency syntax\r\n  * Information status (given, accessible, new, split antecedent)\r\n  * Entity and coreference annotation, including bridging anaphora\r\n  * Entity linking (Wikification)\r\n  * Discourse parses in Rhetorical Structure Theory and discourse dependencies","description_withheld":null,"homepage":"https://gucorpling.org/gum/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"CC-BY-NC-SA","url":"https://github.com/amir-zeldes/gum/blob/master/LICENSE.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"},{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"},{"name":"Relation Classification","url":"/task/relation-classification","datasets_with_task":"/datasets/task/relation-classification"},{"name":"Named Entity Recognition","url":"/task/named-entity-recognition-1","datasets_with_task":"/datasets/task/named-entity-recognition-1"},{"name":"Entity Typing","url":"/task/entity-typing","datasets_with_task":"/datasets/task/entity-typing"},{"name":"Nested Named Entity Recognition","url":"/task/nested-named-entity-recognition","datasets_with_task":"/datasets/task/nested-named-entity-recognition"},{"name":"Discourse Parsing","url":"/task/discourse-parsing","datasets_with_task":"/datasets/task/discourse-parsing"},{"name":"Nested Mention Recognition","url":"/task/nested-mention-recognition","datasets_with_task":"/datasets/task/nested-mention-recognition"},{"name":"Timex normalization","url":"/task/timex-normalization","datasets_with_task":"/datasets/task/timex-normalization"},{"name":"Bridging Anaphora Resolution","url":"/task/bridging-anaphora-resolution","datasets_with_task":"/datasets/task/bridging-anaphora-resolution"},{"name":"Lemmatization","url":"/task/lemmatization","datasets_with_task":"/datasets/task/lemmatization"},{"name":"Discourse Segmentation","url":"/task/discourse-segmentation","datasets_with_task":"/datasets/task/discourse-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GUM"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/entity-linking-on-gum","task":"Entity Linking","dataset_variant":"GUM","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"baseline","paper":"/paper/wikigum-exhaustive-entity-linking-for","metrics":{"F1":"26.4"},"code_links":[]},"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":0,"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/wikigum-exhaustive-entity-linking-for","slug":"wikigum-exhaustive-entity-linking-for","title":"WikiGUM: Exhaustive Entity Linking for Wikification in 12 Genres","date":"2021-09-15","arxiv_id":"2109.07449","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/wikigum-exhaustive-entity-linking-for","slug":"wikigum-exhaustive-entity-linking-for","title":"WikiGUM: Exhaustive Entity Linking for Wikification in 12 Genres","date":"2021-09-15","arxiv_id":"2109.07449","rows_on_this_dataset":1,"code_links":0,"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":"ea4a004e6911e3f8acabac768bb1d683bb5a827f9fcf941b576a6ec77ec797fd","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}