{"url":"/dataset/coauthor","name":"CoAuthor","full_name":null,"description_markdown":"**CoAuthor** is a dataset designed for revealing GPT-3's capabilities in assisting creative and argumentative writing. CoAuthor captures rich interactions between 63 writers and four instances of GPT-3 across 1445 writing sessions.","description_withheld":null,"homepage":"https://coauthor.stanford.edu/","introduced_date":"2022-01-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/coauthor-designing-a-human-ai-collaborative","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","first_author":"Mina Lee","url":null},"license":{"name":"CC BY-SA 4.0","url":"http://creativecommons.org/licenses/by-sa/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Boundary Detection","url":"/task/boundary-detection","datasets_with_task":"/datasets/task/boundary-detection"}],"languages":[],"variants":["CoAuthor"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/boundary-detection-on-coauthor","task":"Boundary Detection","dataset_variant":"CoAuthor","rows":3,"metrics":["Cohen’s Kappa score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B-v0.3)","paper":"/paper/gigacheck-detecting-llm-generated-content","metrics":{"Cohen’s Kappa score":"0.4158"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/gigacheck-detecting-llm-generated-content","title":"GigaCheck: Detecting LLM-generated Content","date":"2024-10-31","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/towards-detecting-ai-generated-text-within","title":"Detecting AI-Generated Sentences in Human-AI Collaborative Hybrid Texts: Challenges, Strategies, and Insights","date":"2024-03-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":6,"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."}