{"url":"/dataset/funcom","name":"Funcom","full_name":null,"description_markdown":"Funcom is a collection of ~2.1 million Java methods and their associated Javadoc comments. This data set was derived from a set of 51 million Java methods and only includes methods that have an associated comment, comments that are in the English language, and has had auto-generated files removed. Each method/comment pair also has an associated method_uid and project_uid so that it is easy to group methods by their parent project.\r\n\r\nThis dataset of function pairs is used for source code summarisation.\r\n\r\nSource: [Funcom](http://leclair.tech/data/funcom/)","description_withheld":null,"homepage":"http://www.leclair.tech/data/funcom","introduced_date":"2019-04-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/recommendations-for-datasets-for-source-code","title":"Recommendations for Datasets for Source Code Summarization","first_author":"Alexander LeClair","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Funcom"],"data_loaders":[{"repo":"https://github.com/go2bharadwaj/CodeSummarizer","url":"https://github.com/go2bharadwaj/CodeSummarizer","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":19,"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."}