{"url":"/dataset/a-ground-truth-dataset-to-identify-bots-in","name":"A ground-truth dataset to identify bots in GitHub","full_name":null,"description_markdown":"This dataset is a ground truth dataset that is used to identify bots. Each account in this dataset is rated by at least 3 raters with a high interrater agreement.","description_withheld":null,"homepage":"https://doi.org/10.5281/zenodo.4000388","introduced_date":"2020-10-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-ground-truth-dataset-and-classification","title":"A ground-truth dataset and classification model for detecting bots in GitHub issue and PR comments","first_author":"Mehdi Golzadeh","url":null},"license":{"name":"Creative Commons Attribution 4.0 International","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[],"tasks":[],"languages":[],"variants":["A ground-truth dataset to identify bots in GitHub"],"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."}