{"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/2010-i2b2-va","name":"2010 i2b2/VA","full_name":"2010 i2b2/VA","description_markdown":"**2010 i2b2/VA** is a biomedical dataset for relation classification and entity typing.","description_withheld":null,"homepage":"https://www.i2b2.org/NLP/Relations/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"FG-1-PG-1","url":"/task/fg-1-pg-1","datasets_with_task":"/datasets/task/fg-1-pg-1"},{"name":"Medical Named Entity Recognition","url":"/task/medical-named-entity-recognition","datasets_with_task":"/datasets/task/medical-named-entity-recognition"},{"name":"Clinical Concept Extraction","url":"/task/clinical-concept-extraction","datasets_with_task":"/datasets/task/clinical-concept-extraction"},{"name":"Clinical Assertion Status Detection","url":"/task/clinical-assertion-status-detection","datasets_with_task":"/datasets/task/clinical-assertion-status-detection"}],"languages":[],"variants":["2010 i2b2/VA"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/clinical-concept-extraction-on-2010-i2b2va","task":"Clinical Concept Extraction","dataset_variant":"2010 i2b2/VA","rows":5,"metrics":["Exact Span F1"],"first_row_in_archive_order":{"model":"BERTlarge (MIMIC)","paper":"/paper/enhancing-clinical-concept-extraction-with","metrics":{"Exact Span F1":"90.25"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/clinical-assertion-status-detection-on-2010","task":"Clinical Assertion Status Detection","dataset_variant":"2010 i2b2/VA","rows":1,"metrics":["Micro F1"],"first_row_in_archive_order":{"model":"BiLSTM (SparkNLP)","paper":"/paper/improving-clinical-document-understanding-on","metrics":{"Micro F1":"0.939"},"code_links":[{"title":"JohnSnowLabs/spark-nlp-workshop","url":"https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/tutorials/Certification_Trainings/Healthcare"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fg-1-pg-1-on-2010-i2b2-va","task":"FG-1-PG-1","dataset_variant":"2010 i2b2/VA","rows":1,"metrics":["F1 (macro)","F1 (micro)"],"first_row_in_archive_order":{"model":"CFNER","paper":"/paper/distilling-causal-effect-from-miscellaneous","metrics":{"F1 (macro)":"0.3626","F1 (micro)":"0.6273"},"code_links":[{"title":"zzz47zzz/CFNER","url":"https://github.com/zzz47zzz/CFNER"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/relation-extraction-on-2010-i2b2-va-1","task":"Relation Extraction","dataset_variant":"2010 i2b2/VA","rows":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"Spark NLP","paper":"/paper/deeper-clinical-document-understanding-using","metrics":{"Macro F1":"69.1"},"code_links":[{"title":"JohnSnowLabs/spark-nlp-workshop","url":"https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Healthcare/10.3.Clinical_RE_SparkNLP_Paper_Reproduce.ipynb"}]},"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":8,"of":8,"counts":{"papers_with_a_benchmark_row":8,"with_a_code_link":5,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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/distilling-causal-effect-from-miscellaneous","slug":"distilling-causal-effect-from-miscellaneous","title":"Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition","date":"2022-10-08","arxiv_id":"2210.03980","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deeper-clinical-document-understanding-using","slug":"deeper-clinical-document-understanding-using","title":"Deeper Clinical Document Understanding Using Relation Extraction","date":"2021-12-25","arxiv_id":"2112.13259","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-clinical-document-understanding-on","slug":"improving-clinical-document-understanding-on","title":"Improving Clinical Document Understanding on COVID-19 Research with Spark NLP","date":"2020-12-07","arxiv_id":"2012.04005","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/characterbert-reconciling-elmo-and-bert-for","slug":"characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","arxiv_id":"2010.10392","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["helboukkouri/character-bert"],"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/characterbert-reconciling-elmo-and-bert-for#ran","syntology_url":"https://syntology.ai/paper/2010.10392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10392"}}}},{"paper":"/paper/cost-effective-selection-of-pretraining-data","slug":"cost-effective-selection-of-pretraining-data","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","date":"2020-10-02","arxiv_id":"2010.01150","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/embedding-strategies-for-specialized-domains","slug":"embedding-strategies-for-specialized-domains","title":"Embedding Strategies for Specialized Domains: Application to Clinical Entity Recognition","date":"2019-07-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhancing-clinical-concept-extraction-with","slug":"enhancing-clinical-concept-extraction-with","title":"Enhancing Clinical Concept Extraction with Contextual Embeddings","date":"2019-02-22","arxiv_id":"1902.08691","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/machine-learned-solutions-for-three-stages-of","slug":"machine-learned-solutions-for-three-stages-of","title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","date":"2011-05-12","arxiv_id":null,"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/distilling-causal-effect-from-miscellaneous","slug":"distilling-causal-effect-from-miscellaneous","title":"Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition","date":"2022-10-08","arxiv_id":"2210.03980","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deeper-clinical-document-understanding-using","slug":"deeper-clinical-document-understanding-using","title":"Deeper Clinical Document Understanding Using Relation Extraction","date":"2021-12-25","arxiv_id":"2112.13259","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-clinical-document-understanding-on","slug":"improving-clinical-document-understanding-on","title":"Improving Clinical Document Understanding on COVID-19 Research with Spark NLP","date":"2020-12-07","arxiv_id":"2012.04005","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/characterbert-reconciling-elmo-and-bert-for","slug":"characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","arxiv_id":"2010.10392","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["helboukkouri/character-bert"],"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/characterbert-reconciling-elmo-and-bert-for#ran","syntology_url":"https://syntology.ai/paper/2010.10392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10392"}}}},{"paper":"/paper/cost-effective-selection-of-pretraining-data","slug":"cost-effective-selection-of-pretraining-data","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","date":"2020-10-02","arxiv_id":"2010.01150","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/embedding-strategies-for-specialized-domains","slug":"embedding-strategies-for-specialized-domains","title":"Embedding Strategies for Specialized Domains: Application to Clinical Entity Recognition","date":"2019-07-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhancing-clinical-concept-extraction-with","slug":"enhancing-clinical-concept-extraction-with","title":"Enhancing Clinical Concept Extraction with Contextual Embeddings","date":"2019-02-22","arxiv_id":"1902.08691","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/machine-learned-solutions-for-three-stages-of","slug":"machine-learned-solutions-for-three-stages-of","title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","date":"2011-05-12","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/2010-i2b2-va/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/2010-i2b2-va/papers/ran/1","json":"/dataset/2010-i2b2-va/papers/ran/1.json","rows":1}],"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":1,"samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"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":"8a440c8226086dd2918d820d0f440146eb1cb9bc6cc0160bc4644bacf3f269b4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}