{"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/medqa-usmle","name":"MedQA","full_name":null,"description_markdown":"Multiple choice question answering based on the United States Medical License Exams (USMLE). The dataset is collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively.","description_withheld":null,"homepage":"https://drive.google.com/file/d/1ImYUSLk9JbgHXOemfvyiDiirluZHPeQw/view","introduced_date":"2020-09-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/what-disease-does-this-patient-have-a-large","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","first_author":"Di Jin","url":null},"license":null,"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[],"variants":["MedQA"],"data_loaders":[{"repo":"https://github.com/Goodnight77/datasets1","url":"https://github.com/Goodnight77/datasets1","frameworks":["tf","pytorch"]}],"num_papers_in_archive":328,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-medqa-usmle","task":"Question Answering","dataset_variant":"MedQA","rows":27,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Med-Gemini","paper":"/paper/capabilities-of-gemini-models-in-medicine","metrics":{"Accuracy":"91.1"},"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":16,"of":16,"counts":{"papers_with_a_benchmark_row":16,"with_a_code_link":12,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":16,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"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/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/medmobile-a-mobile-sized-language-model-with","slug":"medmobile-a-mobile-sized-language-model-with","title":"MedMobile: A mobile-sized language model with expert-level clinical capabilities","date":"2024-10-11","arxiv_id":"2410.09019","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/capabilities-of-gemini-models-in-medicine","slug":"capabilities-of-gemini-models-in-medicine","title":"Capabilities of Gemini Models in Medicine","date":"2024-04-29","arxiv_id":"2404.18416","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/small-language-models-learn-enhanced","slug":"small-language-models-learn-enhanced","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","date":"2024-03-30","arxiv_id":"2404.00376","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/can-generalist-foundation-models-outcompete","slug":"can-generalist-foundation-models-outcompete","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","date":"2023-11-28","arxiv_id":"2311.16452","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-generalist-foundation-models-outcompete#ran","syntology_url":"https://syntology.ai/paper/2311.16452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16452"}}}},{"paper":"/paper/meditron-70b-scaling-medical-pretraining-for","slug":"meditron-70b-scaling-medical-pretraining-for","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","date":"2023-11-27","arxiv_id":"2311.16079","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["epfllm/meditron"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/meditron-70b-scaling-medical-pretraining-for#ran","syntology_url":"https://syntology.ai/paper/2311.16079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16079"}}}},{"paper":"/paper/biomedgpt-open-multimodal-generative-pre","slug":"biomedgpt-open-multimodal-generative-pre","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","date":"2023-08-18","arxiv_id":"2308.09442","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-expert-level-medical-question","slug":"towards-expert-level-medical-question","title":"Towards Expert-Level Medical Question Answering with Large Language Models","date":"2023-05-16","arxiv_id":"2305.09617","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/grapeqa-graph-augmentation-and-pruning-to","slug":"grapeqa-graph-augmentation-and-pruning-to","title":"GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering","date":"2023-03-22","arxiv_id":"2303.12320","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/large-language-models-encode-clinical","slug":"large-language-models-encode-clinical","title":"Large Language Models Encode Clinical Knowledge","date":"2022-12-26","arxiv_id":"2212.13138","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","rows_on_this_dataset":3,"code_links":1,"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":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"paper":"/paper/deep-bidirectional-language-knowledge-graph","slug":"deep-bidirectional-language-knowledge-graph","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","date":"2022-10-17","arxiv_id":"2210.09338","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":1,"official":{"repos":["michiyasunaga/dragon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-bidirectional-language-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2210.09338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09338"}}}},{"paper":"/paper/variational-open-domain-question-answering","slug":"variational-open-domain-question-answering","title":"Variational Open-Domain Question Answering","date":"2022-09-23","arxiv_id":"2210.06345","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["findzebra/fz-openqa","VodLM/vod"],"state":"official (archive's flag): 1 ran","n_ran":1,"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/variational-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/2210.06345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06345"}}}},{"paper":"/paper/can-large-language-models-reason-about","slug":"can-large-language-models-reason-about","title":"Can large language models reason about medical questions?","date":"2022-07-17","arxiv_id":"2207.08143","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["vlievin/medical-reasoning"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-large-language-models-reason-about#ran","syntology_url":"https://syntology.ai/paper/2207.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08143"}}}},{"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":1,"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/biobert-a-pre-trained-biomedical-language","slug":"biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","arxiv_id":"1901.08746","rows_on_this_dataset":2,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":4,"samples_unverified":10,"pointer_only_for_licence":3,"official":{"repos":["dmis-lab/biobert","naver/biobert-pretrained"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/biobert-a-pre-trained-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/1901.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08746"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/medmobile-a-mobile-sized-language-model-with","slug":"medmobile-a-mobile-sized-language-model-with","title":"MedMobile: A mobile-sized language model with expert-level clinical capabilities","date":"2024-10-11","arxiv_id":"2410.09019","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/capabilities-of-gemini-models-in-medicine","slug":"capabilities-of-gemini-models-in-medicine","title":"Capabilities of Gemini Models in Medicine","date":"2024-04-29","arxiv_id":"2404.18416","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/small-language-models-learn-enhanced","slug":"small-language-models-learn-enhanced","title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","date":"2024-03-30","arxiv_id":"2404.00376","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/can-generalist-foundation-models-outcompete","slug":"can-generalist-foundation-models-outcompete","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","date":"2023-11-28","arxiv_id":"2311.16452","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-generalist-foundation-models-outcompete#ran","syntology_url":"https://syntology.ai/paper/2311.16452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16452"}}}},{"paper":"/paper/meditron-70b-scaling-medical-pretraining-for","slug":"meditron-70b-scaling-medical-pretraining-for","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","date":"2023-11-27","arxiv_id":"2311.16079","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["epfllm/meditron"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/meditron-70b-scaling-medical-pretraining-for#ran","syntology_url":"https://syntology.ai/paper/2311.16079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16079"}}}},{"paper":"/paper/biomedgpt-open-multimodal-generative-pre","slug":"biomedgpt-open-multimodal-generative-pre","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","date":"2023-08-18","arxiv_id":"2308.09442","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-expert-level-medical-question","slug":"towards-expert-level-medical-question","title":"Towards Expert-Level Medical Question Answering with Large Language Models","date":"2023-05-16","arxiv_id":"2305.09617","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/grapeqa-graph-augmentation-and-pruning-to","slug":"grapeqa-graph-augmentation-and-pruning-to","title":"GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering","date":"2023-03-22","arxiv_id":"2303.12320","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/large-language-models-encode-clinical","slug":"large-language-models-encode-clinical","title":"Large Language Models Encode Clinical Knowledge","date":"2022-12-26","arxiv_id":"2212.13138","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","rows_on_this_dataset":3,"code_links":1,"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":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"paper":"/paper/deep-bidirectional-language-knowledge-graph","slug":"deep-bidirectional-language-knowledge-graph","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","date":"2022-10-17","arxiv_id":"2210.09338","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":1,"official":{"repos":["michiyasunaga/dragon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-bidirectional-language-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2210.09338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09338"}}}},{"paper":"/paper/variational-open-domain-question-answering","slug":"variational-open-domain-question-answering","title":"Variational Open-Domain Question Answering","date":"2022-09-23","arxiv_id":"2210.06345","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["findzebra/fz-openqa","VodLM/vod"],"state":"official (archive's flag): 1 ran","n_ran":1,"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/variational-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/2210.06345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06345"}}}},{"paper":"/paper/can-large-language-models-reason-about","slug":"can-large-language-models-reason-about","title":"Can large language models reason about medical questions?","date":"2022-07-17","arxiv_id":"2207.08143","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["vlievin/medical-reasoning"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-large-language-models-reason-about#ran","syntology_url":"https://syntology.ai/paper/2207.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08143"}}}},{"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":1,"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/biobert-a-pre-trained-biomedical-language","slug":"biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","arxiv_id":"1901.08746","rows_on_this_dataset":2,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":4,"samples_unverified":10,"pointer_only_for_licence":3,"official":{"repos":["dmis-lab/biobert","naver/biobert-pretrained"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/biobert-a-pre-trained-biomedical-language#ran","syntology_url":"https://syntology.ai/paper/1901.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08746"}}}}],"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/dataset/medqa-usmle/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/medqa-usmle/papers/ran/1","json":"/dataset/medqa-usmle/papers/ran/1.json","rows":8}],"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":8,"samples_harvested":94,"samples_ran":58,"samples_constructed":0,"samples_ran_checked":53,"samples_ran_instrument_failed":5,"samples_unverified":36,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":8,"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":17,"papers_placed":3,"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/question-answering-on-medqa-usmle","since_archive":"/sota/question-answering-on-medqa-usmle#since-judged","papers_judged":17,"placed":3}]},"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":"2541951c26c6243d1c4e156d16be2777e2a7373570b4159800d03346cb62cf84","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}