{"url":"/dataset/mixset","name":"MixSet","full_name":"Mixcase Dataset","description_markdown":"MIXSET comprises a total of 3.6k mixtext instances. The dataset features a blend of HWT(human-written text) and MGT(machine-generated text).","description_withheld":null,"homepage":"https://github.com/Dongping-Chen/MixSet","introduced_date":"2024-01-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/llm-as-a-coauthor-the-challenges-of-detecting","title":"LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?","first_author":"Qihui Zhang","url":null},"license":{"name":"MIT","url":"https://opensource.org/license/mit"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Binary text classification","url":"/task/binary-text-classification","datasets_with_task":"/datasets/task/binary-text-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MixSet","MixSet (Binary)"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/binary-text-classification-on-mixset-binary","task":"Binary text classification","dataset_variant":"MixSet (Binary)","rows":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper":"/paper/gigacheck-detecting-llm-generated-content","metrics":{"F1 score":"0.99"},"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":1,"code_links":0,"syntology":null},{"paper":"/paper/llm-as-a-coauthor-the-challenges-of-detecting","title":"LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?","date":"2024-01-11","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":6,"samples_unverified":10,"pointer_only_for_licence":16,"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":16,"samples_ran":6,"samples_unverified":10,"pointer_only_for_licence":16,"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."}