{"url":"/dataset/cmu-book-summary-dataset","name":"CMU Book Summary Dataset","full_name":null,"description_markdown":"This dataset contains plot summaries for 16,559 books extracted from Wikipedia, along with aligned metadata from Freebase, including book author, title, and genre.\r\n\r\nAll data is released under a Creative Commons Attribution-ShareAlike License. For questions or comments, please contact David Bamman (dbamman@cs.cmu.edu).","description_withheld":null,"homepage":"http://www.cs.cmu.edu/~dbamman/booksummaries.html","introduced_date":"2013-05-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/new-alignment-methods-for-discriminative-book","title":"New Alignment Methods for Discriminative Book Summarization","first_author":"David Bamman","url":null},"license":{"name":"Creative Commons Attribution-ShareAlike 3.0 United States","url":"https://creativecommons.org/licenses/by-sa/3.0/us/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CMU Book Summary Dataset"],"data_loaders":[],"num_papers_in_archive":3,"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."}