{"url":"/dataset/simplestories","name":"SimpleStories","full_name":null,"description_markdown":"SimpleStories is a dataset of >2 million model-generated short stories. It was made to train small, interpretable language models on it. The generation process is open-source: To see how the dataset was generated, or to generate some stories yourself, head over to https://github.com/lennart-finke/simple_stories_generate.","description_withheld":null,"homepage":"https://huggingface.co/datasets/SimpleStories/SimpleStories","introduced_date":"2025-04-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/2504-09184","title":"Parameterized Synthetic Text Generation with SimpleStories","first_author":"Lennart Finke","url":null},"license":{"name":"MIT","url":"https://mit-license.org/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["SimpleStories"],"data_loaders":[],"num_papers_in_archive":1,"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."}