{"url":"/dataset/ghostbuster","name":"Ghostbuster","full_name":null,"description_markdown":"The Ghostbusters dataset leverages the GPT-3.5-turbo model for generating texts in the domains of creative writing, news, and student essays, providing 2,000 texts in the first two domains and 1,994 in the latter.","description_withheld":null,"homepage":"https://github.com/vivek3141/ghostbuster-data","introduced_date":"2023-05-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/ghostbuster-detecting-text-ghostwritten-by","title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models","first_author":"Vivek Verma","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":["Ghostbuster","Ghostbuster (All Domains)"],"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/binary-text-classification-on-ghostbuster-all","task":"Binary text classification","dataset_variant":"Ghostbuster (All Domains)","rows":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper":"/paper/gigacheck-detecting-llm-generated-content","metrics":{"F1 score":"1.0"},"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/ghostbuster-detecting-text-ghostwritten-by","title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models","date":"2023-05-24","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}