{"url":"/dataset/codah","name":"CODAH","full_name":"COmmonsense Dataset Adversarially-authored by Humans","description_markdown":"The COmmonsense Dataset Adversarially-authored by Humans (**CODAH**) is an evaluation set for commonsense question-answering in the sentence completion style of SWAG. As opposed to other automatically generated NLI datasets, CODAH is adversarially constructed by humans who can view feedback from a pre-trained model and use this information to design challenging commonsense questions. It contains 2801 questions in total, and uses 5-fold cross validation for evaluation.\r\n\r\nSource: [CODAH Dataset](https://github.com/Websail-NU/CODAH)\r\nImage Source: [https://www.aclweb.org/anthology/W19-2008.pdf](https://www.aclweb.org/anthology/W19-2008.pdf)","description_withheld":null,"homepage":"https://github.com/Websail-NU/CODAH","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/codah-an-adversarially-authored-question","title":"CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense","first_author":"Michael Chen","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"}],"languages":[],"variants":["CODAH"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jaredfern/codah","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/codah","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/Websail-NU/CODAH","url":"https://github.com/Websail-NU/CODAH","frameworks":[]}],"num_papers_in_archive":29,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-codah","task":"Question Answering","dataset_variant":"CODAH","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"G-DAUG-Combo + RoBERTa-Large","paper":"/paper/g-daug-generative-data-augmentation-for","metrics":{"Accuracy":"84.0"},"code_links":[{"title":"yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/common-sense-reasoning-on-codah","task":"Common Sense Reasoning","dataset_variant":"CODAH","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BERT Large","paper":"/paper/aqua-an-adversarially-authored-question","metrics":{"Accuracy":"69.6"},"code_links":[{"title":"Websail-NU/AQuA","url":"https://github.com/Websail-NU/AQuA"},{"title":"iit-nlp-research/chatgpt-crawler","url":"https://github.com/iit-nlp-research/chatgpt-crawler"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/g-daug-generative-data-augmentation-for","title":"Generative Data Augmentation for Commonsense Reasoning","date":"2020-04-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/aqua-an-adversarially-authored-question","title":"CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense","date":"2019-04-08","rows_on_this_dataset":2,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}