{"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/pubmedqa","name":"PubMedQA","full_name":"PubMedQA","description_markdown":"The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts.\r\n\r\nPubMedQA has 1k expert labeled, 61.2k unlabeled and 211.3k artificially generated QA instances.\r\n\r\nSource: [PubMedQA](https://pubmedqa.github.io/)\r\nImage Source: [https://arxiv.org/pdf/1909.06146v1.pdf](https://arxiv.org/pdf/1909.06146v1.pdf)","description_withheld":null,"homepage":"https://pubmedqa.github.io/","introduced_date":"2019-09-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/pubmedqa-a-dataset-for-biomedical-research","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","first_author":"Qiao Jin","url":null},"license":{"name":"Custom","url":"https://pubmedqa.github.io/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Few-Shot Learning","url":"/task/few-shot-learning","datasets_with_task":"/datasets/task/few-shot-learning"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"}],"languages":[],"variants":["PubMedQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/qiaojin/PubMedQA","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/qiaojin/pubmed_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/highnote/pubmed_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pubmed_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/ibm-self-serve-assets/metagen-blended-rag","url":"https://huggingface.co/datasets/Shivam6693/PubMedQA-MetaGenBlendedRAG/blob/main/README.md","frameworks":[]}],"num_papers_in_archive":276,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-pubmedqa","task":"Question Answering","dataset_variant":"PubMedQA","rows":30,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Meditron-70B (CoT + SC)","paper":"/paper/meditron-70b-scaling-medical-pretraining-for","metrics":{"Accuracy":"81.6"},"code_links":[{"title":"epfllm/meditron","url":"https://github.com/epfllm/meditron"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-learning-on-pubmedqa","task":"Few-Shot Learning","dataset_variant":"PubMedQA","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MetaGen Blended RAG (zero-shot)","paper":"/paper/metagen-blended-rag-higher-accuracy-for","metrics":{"Accuracy":"77.9"},"code_links":[{"title":"ibm-self-serve-assets/metagen-blended-rag","url":"https://github.com/ibm-self-serve-assets/metagen-blended-rag"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/retrieval-on-pubmedqa","task":"Retrieval","dataset_variant":"PubMedQA","rows":1,"metrics":["Accuracy (Top-1)"],"first_row_in_archive_order":{"model":"MetaGen Blended RAG","paper":"/paper/metagen-blended-rag-higher-accuracy-for","metrics":{"Accuracy (Top-1)":"82.1"},"code_links":[{"title":"ibm-self-serve-assets/metagen-blended-rag","url":"https://github.com/ibm-self-serve-assets/metagen-blended-rag"}]},"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":17,"of":17,"counts":{"papers_with_a_benchmark_row":17,"with_a_code_link":13,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":17,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"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/metagen-blended-rag-higher-accuracy-for","slug":"metagen-blended-rag-higher-accuracy-for","title":"MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A Without Fine-Tuning","date":"2025-05-23","arxiv_id":"2505.18247","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/rankrag-unifying-context-ranking-with","slug":"rankrag-unifying-context-ranking-with","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","date":"2024-07-02","arxiv_id":"2407.02485","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/evaluation-of-large-language-model","slug":"evaluation-of-large-language-model","title":"Evaluation of large language model performance on the Biomedical Language Understanding and Reasoning Benchmark","date":"2024-05-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mediswift-efficient-sparse-pre-trained","slug":"mediswift-efficient-sparse-pre-trained","title":"MediSwift: Efficient Sparse Pre-trained Biomedical Language Models","date":"2024-03-01","arxiv_id":"2403.00952","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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":1,"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/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","rows_on_this_dataset":2,"code_links":2,"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/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":7,"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/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"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":2,"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/bioelectra-pretrained-biomedical-text-encoder","slug":"bioelectra-pretrained-biomedical-text-encoder","title":"BioELECTRA:Pretrained Biomedical text Encoder using Discriminators","date":"2021-06-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pubmedqa-a-dataset-for-biomedical-research","slug":"pubmedqa-a-dataset-for-biomedical-research","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","date":"2019-09-13","arxiv_id":"1909.06146","rows_on_this_dataset":1,"code_links":5,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/metagen-blended-rag-higher-accuracy-for","slug":"metagen-blended-rag-higher-accuracy-for","title":"MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A Without Fine-Tuning","date":"2025-05-23","arxiv_id":"2505.18247","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/rankrag-unifying-context-ranking-with","slug":"rankrag-unifying-context-ranking-with","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","date":"2024-07-02","arxiv_id":"2407.02485","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/evaluation-of-large-language-model","slug":"evaluation-of-large-language-model","title":"Evaluation of large language model performance on the Biomedical Language Understanding and Reasoning Benchmark","date":"2024-05-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mediswift-efficient-sparse-pre-trained","slug":"mediswift-efficient-sparse-pre-trained","title":"MediSwift: Efficient Sparse Pre-trained Biomedical Language Models","date":"2024-03-01","arxiv_id":"2403.00952","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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":1,"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/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","rows_on_this_dataset":2,"code_links":2,"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/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":7,"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/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"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":2,"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/bioelectra-pretrained-biomedical-text-encoder","slug":"bioelectra-pretrained-biomedical-text-encoder","title":"BioELECTRA:Pretrained Biomedical text Encoder using Discriminators","date":"2021-06-11","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pubmedqa-a-dataset-for-biomedical-research","slug":"pubmedqa-a-dataset-for-biomedical-research","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","date":"2019-09-13","arxiv_id":"1909.06146","rows_on_this_dataset":1,"code_links":5,"syntology":null}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/pubmedqa/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/pubmedqa/papers/ran/1","json":"/dataset/pubmedqa/papers/ran/1.json","rows":4}],"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":4,"samples_harvested":40,"samples_ran":24,"samples_constructed":0,"samples_ran_checked":24,"samples_ran_instrument_failed":0,"samples_unverified":16,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":4,"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":8,"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/question-answering-on-pubmedqa","since_archive":"/sota/question-answering-on-pubmedqa#since-judged","papers_judged":8,"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":"5aac3d8f0641b548322a4dab31f42007c7a1e9b8802bd6f481642f1209945eb8","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}