{"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/medconceptsqa","name":"MedConceptsQA","full_name":null,"description_markdown":"MedConceptsQA - Open Source Medical Concepts QA Benchmark\r\n\r\nThe benchmark can be found here: \r\nhttps://huggingface.co/datasets/ofir408/MedConceptsQA","description_withheld":null,"homepage":"https://huggingface.co/datasets/ofir408/MedConceptsQA","introduced_date":"2024-05-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/medconceptsqa-open-source-medical-concepts-qa","title":"MedConceptsQA: Open Source Medical Concepts QA Benchmark","first_author":"Ofir Ben Shoham","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"},{"name":"Large Language Model","url":"/task/large-language-model","datasets_with_task":"/datasets/task/large-language-model"},{"name":"Medical Diagnosis","url":"/task/medical-diagnosis","datasets_with_task":"/datasets/task/medical-diagnosis"},{"name":"Medical Procedure","url":"/task/medical-procedure","datasets_with_task":"/datasets/task/medical-procedure"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MedConceptsQA"],"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/zero-shot-learning-on-medconceptsqa","task":"Zero-Shot Learning","dataset_variant":"MedConceptsQA","rows":13,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"gpt-4-0125-preview","paper":"/paper/gpt-4-technical-report-1","metrics":{"Accuracy":"52.489"},"code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-learning-on-medconceptsqa","task":"Few-Shot Learning","dataset_variant":"MedConceptsQA","rows":12,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"gpt-4-0125-preview","paper":"/paper/gpt-4-technical-report-1","metrics":{"Accuracy":"61.911"},"code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}]},"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":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":10,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/medconceptsqa-open-source-medical-concepts-qa","slug":"medconceptsqa-open-source-medical-concepts-qa","title":"MedConceptsQA: Open Source Medical Concepts QA Benchmark","date":"2024-05-12","arxiv_id":"2405.07348","rows_on_this_dataset":1,"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":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["nadavlab/MedConceptsQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"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/medconceptsqa-open-source-medical-concepts-qa#ran","syntology_url":"https://syntology.ai/paper/2405.07348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07348"}}}},{"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/biomistral-a-collection-of-open-source","slug":"biomistral-a-collection-of-open-source","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","date":"2024-02-15","arxiv_id":"2402.10373","rows_on_this_dataset":2,"code_links":1,"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":1,"official":{"repos":["biomistral/biomistral"],"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/biomistral-a-collection-of-open-source#ran","syntology_url":"https://syntology.ai/paper/2402.10373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10373"}}}},{"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":4,"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/zephyr-direct-distillation-of-lm-alignment","slug":"zephyr-direct-distillation-of-lm-alignment","title":"Zephyr: Direct Distillation of LM Alignment","date":"2023-10-25","arxiv_id":"2310.16944","rows_on_this_dataset":2,"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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zephyr-direct-distillation-of-lm-alignment#ran","syntology_url":"https://syntology.ai/paper/2310.16944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16944"}}}},{"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":2,"code_links":1,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":2,"code_links":11,"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":1,"official":{"repos":["openai/evals"],"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/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":2,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"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/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/gatortron-a-large-clinical-language-model-to","slug":"gatortron-a-large-clinical-language-model-to","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","date":"2022-02-02","arxiv_id":"2203.03540","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/clinical-longformer-and-clinical-bigbird","slug":"clinical-longformer-and-clinical-bigbird","title":"Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences","date":"2022-01-27","arxiv_id":"2201.11838","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"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/medconceptsqa-open-source-medical-concepts-qa","slug":"medconceptsqa-open-source-medical-concepts-qa","title":"MedConceptsQA: Open Source Medical Concepts QA Benchmark","date":"2024-05-12","arxiv_id":"2405.07348","rows_on_this_dataset":1,"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":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["nadavlab/MedConceptsQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"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/medconceptsqa-open-source-medical-concepts-qa#ran","syntology_url":"https://syntology.ai/paper/2405.07348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07348"}}}},{"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/biomistral-a-collection-of-open-source","slug":"biomistral-a-collection-of-open-source","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","date":"2024-02-15","arxiv_id":"2402.10373","rows_on_this_dataset":2,"code_links":1,"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":1,"official":{"repos":["biomistral/biomistral"],"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/biomistral-a-collection-of-open-source#ran","syntology_url":"https://syntology.ai/paper/2402.10373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10373"}}}},{"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":4,"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/zephyr-direct-distillation-of-lm-alignment","slug":"zephyr-direct-distillation-of-lm-alignment","title":"Zephyr: Direct Distillation of LM Alignment","date":"2023-10-25","arxiv_id":"2310.16944","rows_on_this_dataset":2,"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":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/zephyr-direct-distillation-of-lm-alignment#ran","syntology_url":"https://syntology.ai/paper/2310.16944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16944"}}}},{"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":2,"code_links":1,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":2,"code_links":11,"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":1,"official":{"repos":["openai/evals"],"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/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":2,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"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/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/gatortron-a-large-clinical-language-model-to","slug":"gatortron-a-large-clinical-language-model-to","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","date":"2022-02-02","arxiv_id":"2203.03540","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/clinical-longformer-and-clinical-bigbird","slug":"clinical-longformer-and-clinical-bigbird","title":"Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences","date":"2022-01-27","arxiv_id":"2201.11838","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"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/medconceptsqa/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/medconceptsqa/papers/ran/1","json":"/dataset/medconceptsqa/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":171,"samples_ran":115,"samples_constructed":9,"samples_ran_checked":89,"samples_ran_instrument_failed":26,"samples_unverified":56,"pointer_only_for_licence":19,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":8,"papers_with_a_run_with_no_instrument_failure":7,"papers_where_every_run_was_an_instrument_failure":1,"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":"7f1d026dc77310b56b073f3e69e8780828024cebca94ff792b05590350863eab","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}