{"url":"/dataset/common-crawl","name":"Common Crawl","full_name":null,"description_markdown":"The Common Crawl corpus contains petabytes of data collected over 12 years of web crawling. The corpus contains raw web page data, metadata extracts and text extracts. Common Crawl data is stored on Amazon Web Services’ Public Data Sets and on multiple academic cloud platforms across the world.","description_withheld":null,"homepage":"https://commoncrawl.org/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Common Crawl"],"data_loaders":[],"num_papers_in_archive":2,"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."}