{"url":"/dataset/proto-summ","name":"Proto Summ","full_name":null,"description_markdown":"This is a large-scale court judgment dataset, where each judgment is a summary of the case description with a patternized style. It contains 2,003,390 court judgment documents. The case description is used as the input, and the court judgment as the summary. The average lengths of the input documents and summaries are 595.15 words and 273.57 words respectively.\n\nSource: [https://arxiv.org/pdf/1909.08837.pdf](https://arxiv.org/pdf/1909.08837.pdf)","description_withheld":null,"homepage":"https://github.com/gsh199449/proto-summ","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/how-to-write-summaries-with-patterns-learning","title":"How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing","first_author":"Shen Gao","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Proto Summ"],"data_loaders":[{"repo":"https://github.com/gsh199449/proto-summ","url":"https://github.com/gsh199449/proto-summ","frameworks":[]}],"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."}