{"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/bc5cdr","name":"BC5CDR","full_name":"BioCreative V CDR corpus","description_markdown":"**BC5CDR** corpus consists of 1500 PubMed articles with 4409 annotated chemicals, 5818 diseases and 3116 chemical-disease interactions.\r\n\r\nSource: [https://www.ncbi.nlm.nih.gov/research/bionlp/Data/](https://www.ncbi.nlm.nih.gov/research/bionlp/Data/)\r\nImage Source: [https://arxiv.org/pdf/1805.10586.pdf](https://arxiv.org/pdf/1805.10586.pdf)","description_withheld":null,"homepage":"https://github.com/JHnlp/BioCreative-V-CDR-Corpus","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"BioCreative V CDR task corpus: a resource for chemical disease relation extraction","first_author":null,"url":"https://doi.org/10.1093/database/baw068"},"license":{"name":"Custom","url":"https://biocreative.bioinformatics.udel.edu/tasks/biocreative-v/track-3-cdr/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"UIE","url":"/task/uie","datasets_with_task":"/datasets/task/uie"},{"name":"Weakly-Supervised Named Entity Recognition","url":"/task/weakly-supervised-named-entity-recognition","datasets_with_task":"/datasets/task/weakly-supervised-named-entity-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["BC5CDR","BC5CDR-disease","BC5CDR-chemical"],"data_loaders":[{"repo":"https://github.com/sq1balaji/EasyOCR-ChatBot","url":"https://github.com/sq1balaji/EasyOCR-ChatBot","frameworks":["tf","pytorch"]}],"num_papers_in_archive":191,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-ner-on-bc5cdr","task":"Named Entity Recognition (NER)","dataset_variant":"BC5CDR","rows":16,"metrics":["F1"],"first_row_in_archive_order":{"model":"BINDER","paper":"/paper/optimizing-bi-encoder-for-named-entity","metrics":{"F1":"91.9"},"code_links":[{"title":"microsoft/binder","url":"https://github.com/microsoft/binder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/named-entity-recognition-on-bc5cdr-chemical","task":"Named Entity Recognition (NER)","dataset_variant":"BC5CDR-chemical","rows":13,"metrics":["F1"],"first_row_in_archive_order":{"model":"Spark NLP","paper":"/paper/biomedical-named-entity-recognition-at-scale","metrics":{"F1":"94.88"},"code_links":[{"title":"JohnSnowLabs/spark-nlp-workshop","url":"https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Healthcare/1.4.Biomedical_NER_SparkNLP_paper_reproduce.ipynb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/named-entity-recognition-on-bc5cdr-disease","task":"Named Entity Recognition (NER)","dataset_variant":"BC5CDR-disease","rows":10,"metrics":["F1"],"first_row_in_archive_order":{"model":"BioMegatron","paper":"/paper/biomegatron-larger-biomedical-domain-language","metrics":{"F1":"88.5"},"code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/uie-on-bc5cdr","task":"UIE","dataset_variant":"BC5CDR","rows":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"KnowCoder-7b-IE","paper":"/paper/knowcoder-coding-structured-knowledge-into","metrics":{"F1 score":"89.3"},"code_links":[{"title":"ICT-GoKnow/KnowCoder","url":"https://github.com/ICT-GoKnow/KnowCoder"}]},"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":22,"of":22,"counts":{"papers_with_a_benchmark_row":22,"with_a_code_link":22,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":7,"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/knowcoder-coding-structured-knowledge-into","slug":"knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","arxiv_id":"2403.07969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gollie-annotation-guidelines-improve-zero","slug":"gollie-annotation-guidelines-improve-zero","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","date":"2023-10-05","arxiv_id":"2310.03668","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":18,"samples_constructed":2,"samples_ran_checked":17,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["hitz-zentroa/gollie"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":2,"n_ran_no_instrument_failure":17,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gollie-annotation-guidelines-improve-zero#ran","syntology_url":"https://syntology.ai/paper/2310.03668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03668"}}}},{"paper":"/paper/universalner-targeted-distillation-from-large","slug":"universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","arxiv_id":"2308.03279","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universalner-targeted-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2308.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03279"}}}},{"paper":"/paper/enhancing-label-consistency-on-document-level","slug":"enhancing-label-consistency-on-document-level","title":"Enhancing Label Consistency on Document-level Named Entity Recognition","date":"2022-10-24","arxiv_id":"2210.12949","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/on-the-effectiveness-of-compact-biomedical","slug":"on-the-effectiveness-of-compact-biomedical","title":"On the Effectiveness of Compact Biomedical Transformers","date":"2022-09-07","arxiv_id":"2209.03182","rows_on_this_dataset":8,"code_links":1,"syntology":null},{"paper":"/paper/optimizing-bi-encoder-for-named-entity","slug":"optimizing-bi-encoder-for-named-entity","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","date":"2022-08-30","arxiv_id":"2208.14565","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["microsoft/binder"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/optimizing-bi-encoder-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/2208.14565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.14565"}}}},{"paper":"/paper/accurate-clinical-and-biomedical-named-entity","slug":"accurate-clinical-and-biomedical-named-entity","title":"Accurate clinical and biomedical Named entity recognition at scale","date":"2022-07-19","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hero-gang-neural-model-for-named-entity","slug":"hero-gang-neural-model-for-named-entity","title":"Hero-Gang Neural Model For Named Entity Recognition","date":"2022-05-15","arxiv_id":"2205.07177","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/focusing-on-possible-named-entities-in-active","slug":"focusing-on-possible-named-entities-in-active","title":"Focusing on Potential Named Entities During Active Label Acquisition","date":"2021-11-06","arxiv_id":"2111.03837","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scifive-a-text-to-text-transformer-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.03598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03598"}}}},{"paper":"/paper/improving-named-entity-recognition-by","slug":"improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","arxiv_id":"2105.03654","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["modelscope/adaseq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-named-entity-recognition-by#ran","syntology_url":"https://syntology.ai/paper/2105.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03654"}}}},{"paper":"/paper/improving-biomedical-pretrained-language","slug":"improving-biomedical-pretrained-language","title":"Improving Biomedical Pretrained Language Models with Knowledge","date":"2021-04-21","arxiv_id":"2104.10344","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/electramed-a-new-pre-trained-language","slug":"electramed-a-new-pre-trained-language","title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","date":"2021-04-19","arxiv_id":"2104.09585","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-robust-and-domain-adaptive-approach-for-low","slug":"a-robust-and-domain-adaptive-approach-for-low","title":"A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition","date":"2021-01-02","arxiv_id":"2101.00388","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-biomedical-named-entity-recognition","slug":"improving-biomedical-named-entity-recognition","title":"Improving Biomedical Named Entity Recognition with Syntactic Information","date":"2020-11-25","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/biomedical-named-entity-recognition-at-scale","slug":"biomedical-named-entity-recognition-at-scale","title":"Biomedical Named Entity Recognition at Scale","date":"2020-11-12","arxiv_id":"2011.06315","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/biomegatron-larger-biomedical-domain-language","slug":"biomegatron-larger-biomedical-domain-language","title":"BioMegatron: Larger Biomedical Domain Language Model","date":"2020-10-12","arxiv_id":"2010.06060","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/transfer-learning-in-biomedical-natural","slug":"transfer-learning-in-biomedical-natural","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","date":"2019-06-13","arxiv_id":"1906.05474","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ncbi-nlp/BLUE_Benchmark","ncbi-nlp/NCBI_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/transfer-learning-in-biomedical-natural#ran","syntology_url":"https://syntology.ai/paper/1906.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05474"}}}},{"paper":"/paper/an-attention-based-bilstm-crf-approach-to","slug":"an-attention-based-bilstm-crf-approach-to","title":"An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition","date":"2019-04-15","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scibert-pretrained-contextualized-embeddings","slug":"scibert-pretrained-contextualized-embeddings","title":"SciBERT: A Pretrained Language Model for Scientific Text","date":"2019-03-26","arxiv_id":"1903.10676","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/collabonet-collaboration-of-deep-neural","slug":"collabonet-collaboration-of-deep-neural","title":"CollaboNet: collaboration of deep neural networks for biomedical named entity recognition","date":"2018-09-21","arxiv_id":"1809.07950","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/knowcoder-coding-structured-knowledge-into","slug":"knowcoder-coding-structured-knowledge-into","title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","date":"2024-03-12","arxiv_id":"2403.07969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gollie-annotation-guidelines-improve-zero","slug":"gollie-annotation-guidelines-improve-zero","title":"GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction","date":"2023-10-05","arxiv_id":"2310.03668","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":18,"samples_constructed":2,"samples_ran_checked":17,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["hitz-zentroa/gollie"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":2,"n_ran_no_instrument_failure":17,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gollie-annotation-guidelines-improve-zero#ran","syntology_url":"https://syntology.ai/paper/2310.03668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03668"}}}},{"paper":"/paper/universalner-targeted-distillation-from-large","slug":"universalner-targeted-distillation-from-large","title":"UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition","date":"2023-08-07","arxiv_id":"2308.03279","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":4,"samples_unverified":4,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/universalner-targeted-distillation-from-large#ran","syntology_url":"https://syntology.ai/paper/2308.03279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03279"}}}},{"paper":"/paper/enhancing-label-consistency-on-document-level","slug":"enhancing-label-consistency-on-document-level","title":"Enhancing Label Consistency on Document-level Named Entity Recognition","date":"2022-10-24","arxiv_id":"2210.12949","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/on-the-effectiveness-of-compact-biomedical","slug":"on-the-effectiveness-of-compact-biomedical","title":"On the Effectiveness of Compact Biomedical Transformers","date":"2022-09-07","arxiv_id":"2209.03182","rows_on_this_dataset":8,"code_links":1,"syntology":null},{"paper":"/paper/optimizing-bi-encoder-for-named-entity","slug":"optimizing-bi-encoder-for-named-entity","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","date":"2022-08-30","arxiv_id":"2208.14565","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["microsoft/binder"],"state":"official (archive's flag): 4 ran","n_ran":4,"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/optimizing-bi-encoder-for-named-entity#ran","syntology_url":"https://syntology.ai/paper/2208.14565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.14565"}}}},{"paper":"/paper/accurate-clinical-and-biomedical-named-entity","slug":"accurate-clinical-and-biomedical-named-entity","title":"Accurate clinical and biomedical Named entity recognition at scale","date":"2022-07-19","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hero-gang-neural-model-for-named-entity","slug":"hero-gang-neural-model-for-named-entity","title":"Hero-Gang Neural Model For Named Entity Recognition","date":"2022-05-15","arxiv_id":"2205.07177","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/focusing-on-possible-named-entities-in-active","slug":"focusing-on-possible-named-entities-in-active","title":"Focusing on Potential Named Entities During Active Label Acquisition","date":"2021-11-06","arxiv_id":"2111.03837","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scifive-a-text-to-text-transformer-model-for","slug":"scifive-a-text-to-text-transformer-model-for","title":"SciFive: a text-to-text transformer model for biomedical literature","date":"2021-05-28","arxiv_id":"2106.03598","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["justinphan3110/SciFive"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scifive-a-text-to-text-transformer-model-for#ran","syntology_url":"https://syntology.ai/paper/2106.03598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03598"}}}},{"paper":"/paper/improving-named-entity-recognition-by","slug":"improving-named-entity-recognition-by","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","date":"2021-05-08","arxiv_id":"2105.03654","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["modelscope/adaseq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-named-entity-recognition-by#ran","syntology_url":"https://syntology.ai/paper/2105.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03654"}}}},{"paper":"/paper/improving-biomedical-pretrained-language","slug":"improving-biomedical-pretrained-language","title":"Improving Biomedical Pretrained Language Models with Knowledge","date":"2021-04-21","arxiv_id":"2104.10344","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/electramed-a-new-pre-trained-language","slug":"electramed-a-new-pre-trained-language","title":"ELECTRAMed: a new pre-trained language representation model for biomedical NLP","date":"2021-04-19","arxiv_id":"2104.09585","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-robust-and-domain-adaptive-approach-for-low","slug":"a-robust-and-domain-adaptive-approach-for-low","title":"A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition","date":"2021-01-02","arxiv_id":"2101.00388","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-biomedical-named-entity-recognition","slug":"improving-biomedical-named-entity-recognition","title":"Improving Biomedical Named Entity Recognition with Syntactic Information","date":"2020-11-25","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/biomedical-named-entity-recognition-at-scale","slug":"biomedical-named-entity-recognition-at-scale","title":"Biomedical Named Entity Recognition at Scale","date":"2020-11-12","arxiv_id":"2011.06315","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/biomegatron-larger-biomedical-domain-language","slug":"biomegatron-larger-biomedical-domain-language","title":"BioMegatron: Larger Biomedical Domain Language Model","date":"2020-10-12","arxiv_id":"2010.06060","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/transfer-learning-in-biomedical-natural","slug":"transfer-learning-in-biomedical-natural","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","date":"2019-06-13","arxiv_id":"1906.05474","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ncbi-nlp/BLUE_Benchmark","ncbi-nlp/NCBI_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/transfer-learning-in-biomedical-natural#ran","syntology_url":"https://syntology.ai/paper/1906.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05474"}}}},{"paper":"/paper/an-attention-based-bilstm-crf-approach-to","slug":"an-attention-based-bilstm-crf-approach-to","title":"An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition","date":"2019-04-15","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scibert-pretrained-contextualized-embeddings","slug":"scibert-pretrained-contextualized-embeddings","title":"SciBERT: A Pretrained Language Model for Scientific Text","date":"2019-03-26","arxiv_id":"1903.10676","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/collabonet-collaboration-of-deep-neural","slug":"collabonet-collaboration-of-deep-neural","title":"CollaboNet: collaboration of deep neural networks for biomedical named entity recognition","date":"2018-09-21","arxiv_id":"1809.07950","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/dataset/bc5cdr/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/bc5cdr/papers/ran/1","json":"/dataset/bc5cdr/papers/ran/1.json","rows":7}],"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":7,"samples_harvested":66,"samples_ran":44,"samples_constructed":2,"samples_ran_checked":36,"samples_ran_instrument_failed":8,"samples_unverified":22,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":7,"papers_with_a_run_with_no_instrument_failure":7,"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/named-entity-recognition-ner-on-bc5cdr","since_archive":"/sota/named-entity-recognition-ner-on-bc5cdr#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":"dd8ba39258c8c6a0e48df764b35ebaa6551ae8b2f9269f682fd263a894bc47d4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}