{"url":"/dataset/common-crawl-domain-names","name":"Common Crawl Domain Names","full_name":null,"description_markdown":"Corpus of domain names scraped from Common Crawl and manually annotated to add word boundaries (e.g. \"commoncrawl\" to \"common crawl\").\r\n\r\nSource: [Common Crawl Domain Names](https://github.com/google-research-datasets/common-crawl-domain-names)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/common-crawl-domain-names","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Common Crawl Domain Names"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/crawl_domain","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/crawl_domain","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research-datasets/common-crawl-domain-names","url":"https://github.com/google-research-datasets/common-crawl-domain-names","frameworks":[]}],"num_papers_in_archive":0,"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."}