{"url":"/dataset/geography-of-open-source-software","name":"Geography of Open Source Software","full_name":null,"description_markdown":"This dataset reports counts of active GitHub contributors (activity: 2019/2020) geolocated in early 2021. Counts are aggregated at the country level and at various regional scales. Besides countries, we report data on the EU NUTS2 level, for Brazilian, Russian, Chinese, Japanese, Indian, and US-American subnational geographies. We used a pipeline approach, attempting to infer location first from GitHub profile of a developer, then from linked Twitter accounts, then from email suffixes (country level only). Our data reports the count of developers identified by each stage of the pipeline, in case for instance one prefers to only use the GitHub account information.","description_withheld":null,"homepage":"https://github.com/johanneswachs/OSS_Geography_Data","introduced_date":"2021-07-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-geography-of-open-source-software","title":"The Geography of Open Source Software: Evidence from GitHub","first_author":null,"url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Geography of Open Source Software"],"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":"2026-09-24T18:15:14+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."}