{"url":"/dataset/cc-news","name":"CC-News","full_name":"CommonCrawl News dataset","description_markdown":"**CommonCrawl News** is a dataset containing news articles from news sites all over the world. The dataset is available in form of Web ARChive (WARC) files that are released on a daily basis.\r\n\r\nSource: [https://commoncrawl.org/2016/10/news-dataset-available/](https://commoncrawl.org/2016/10/news-dataset-available/)","description_withheld":null,"homepage":"https://commoncrawl.org/2016/10/news-dataset-available/","introduced_date":"2016-10-04","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Multilingual","url":"/datasets/language/multilingual"}],"variants":["CC-News"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/vblagoje/cc_news","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cc_news","frameworks":["tf","pytorch","jax"]}],"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."}