{"url":"/dataset/realnews","name":"RealNews","full_name":null,"description_markdown":"**RealNews** is a large corpus of news articles from Common Crawl. Data is scraped from Common Crawl, limited to the 5000 news domains indexed by Google News. The authors used the Newspaper Python library to extract the body and metadata from each article. News from Common Crawl dumps from December 2016 through March 2019\r\nwere used as training data; articles published in April 2019 from the April 2019 dump were used for evaluation. After deduplication, RealNews is 120 gigabytes without compression.\r\n\r\nImage Source: [https://arxiv.org/pdf/1905.12616v3.pdf](https://arxiv.org/pdf/1905.12616v3.pdf)","description_withheld":null,"homepage":"https://github.com/rowanz/grover/tree/master/realnews","introduced_date":"2019-05-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/defending-against-neural-fake-news","title":"Defending Against Neural Fake News","first_author":"Rowan Zellers","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"https://docs.google.com/forms/d/1LMAUeUtHNPXO9koyAIlDpvyKsLSYlrBj3rYhC30a7Ak"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Fake News Detection","url":"/task/fake-news-detection","datasets_with_task":"/datasets/task/fake-news-detection"}],"languages":[],"variants":["RealNews"],"data_loaders":[{"repo":"https://github.com/rowanz/grover","url":"https://github.com/rowanz/grover","frameworks":["tf"]}],"num_papers_in_archive":80,"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."}