{"url":"/dataset/pasa","name":"PaSa","full_name":null,"description_markdown":"**PaSa** is a dataset to train Machine Learning algorithms to automate the highlighting of patent paragraphs with semantic annotations. It consists of 150k samples obtained by traversing USPTO patents over a decade","description_withheld":null,"homepage":"https://github.com/Renuk9390/Patent_Sentiment_Analysis","introduced_date":"2021-11-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/patent-sentiment-analysis-to-highlight-patent","title":"Patent Sentiment Analysis to Highlight Patent Paragraphs","first_author":"Renukswamy Chikkamath","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PaSa"],"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":"2026-09-25T09:33:49+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."}