{"url":"/dataset/webbrain-raw","name":"WebBrain-Raw","full_name":null,"description_markdown":"**WebBrain-Raw** is a large-scale dataset built from English Wikipedia articles and their crawlable Wikipedia references. It comprises 153 zipped data chunks in which each line is a Wikipedia page with its reference articles.\r\n\r\nSource: [WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus](https://arxiv.org/pdf/2304.04358v1.pdf)","description_withheld":null,"homepage":"https://github.com/qhjqhj00/WebBrain-Data","introduced_date":"2023-04-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/webbrain-learning-to-generate-factually","title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","first_author":"Hongjing Qian","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/qhjqhj00/WebBrain-Data/blob/main/LICENSE"},"modalities":[],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WebBrain-Raw"],"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."}