{"url":"/dataset/public-git-archive","name":"Public Git Archive","full_name":null,"description_markdown":"The **Public Git Archive** is a dataset of 182,014 top-bookmarked Git repositories from GitHub totalling 6 TB. The dataset provides the source code of the projects, the related metadata, and development history.","description_withheld":null,"homepage":"https://github.com/src-d/datasets/tree/master/PublicGitArchive","introduced_date":"2018-03-20","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Public Git Archive: a Big Code dataset for all","first_author":null,"url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[],"languages":[],"variants":["Public Git Archive"],"data_loaders":[{"repo":"https://github.com/src-d/datasets","url":"https://github.com/src-d/datasets","frameworks":[]}],"num_papers_in_archive":5,"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."}