{"url":"/dataset/pippa","name":"PIPPA","full_name":null,"description_markdown":"PIPPA (Personal Interaction Pairs between People and AI) is a partially-synthetic dataset. The dataset comprises over 1 million utterances that are distributed across 26,000 conversation sessions and provides a rich resource for researchers and AI developers to explore and refine conversational AI systems in the context of role-play scenarios.","description_withheld":null,"homepage":"https://huggingface.co/datasets/PygmalionAI/PIPPA","introduced_date":"2023-08-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/pippa-a-partially-synthetic-conversational","title":"PIPPA: A Partially Synthetic Conversational Dataset","first_author":"Tear Gosling","url":null},"license":{"name":"AGPL-3.0 license","url":"https://huggingface.co/datasets?license=license%3Aagpl-3.0"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["PIPPA"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+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."}