{"entity_id":"common-crawl","claims":10,"verified_share":1,"sources":{"total":5,"by_quality_band":{"authoritative":0,"professional":0,"informal":5,"unknown":0},"distinct_publishers":5,"recency":{"under_90d":0,"under_365d":0,"older":0,"undated":5}},"agreement":{"stances_recorded":0,"refute_rate":null,"claims":[{"claim_id":"clm_513fef7c-e572-4e30-b502-84f92b45011f","statement":"Common Crawl is the largest freely available source of web crawl data and has become pivotal to the development of gener","verified":true,"asserted_confidence":0.95,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_3bbcec47-ae3c-4bf0-8405-dbfcb7810457","statement":"Common Crawl has been used by AI companies including OpenAI, Google, Anthropic, Nvidia, Meta, and Amazon to train large ","verified":true,"asserted_confidence":0.9,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_5a466fba-90e0-42d4-a243-9217c17775f5","statement":"Common Crawl hosts several AI-training data sets derived from its crawls, including one for Nvidia, the most valuable co","verified":true,"asserted_confidence":0.85,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_fd232023-1108-4c0f-9997-e3893e3e2416","statement":"Common Crawl was founded in 2007 by Gil Elbaz, who previously co-founded Applied Semantics, acquired by Google in 2003 f","verified":true,"asserted_confidence":0.9,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_aa831580-ef0a-4edb-9944-3d6d7e9840f1","statement":"The entire Common Crawl archive is hosted through the AWS Open Data program, meaning anyone can access it without paying","verified":true,"asserted_confidence":0.9,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_177d87cb-e398-4c59-b025-3825cdff5a2c","statement":"Common Crawl began collecting data in 2008 using a custom Hadoop-based crawler with a PageRank implementation.","verified":true,"asserted_confidence":0.85,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_28c73074-b483-4b50-b8b5-6f2cbae5e222","statement":"Common Crawl releases monthly datasets containing petabytes of crawled web pages including raw WARC files, text-only ext","verified":true,"asserted_confidence":0.85,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_7836a0f8-9103-4c64-8b4c-b0c0c6eb0de9","statement":"Common Crawl democratizes access to web-scale data that was previously only available to companies with massive crawling","verified":true,"asserted_confidence":0.9,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_dee270b1-1b0f-4e21-9dfa-8ab2c3eeaf05","statement":"Common Crawl's database is large enough to be measured in petabytes.","verified":true,"asserted_confidence":0.85,"supports":0,"refutes":0,"corroborated":null},{"claim_id":"clm_d08b61b8-d5ec-4651-9697-c6a58a4024f6","statement":"Common Crawl collaborates with organizations including Open Web Search, Software Heritage, and Tola Capital.","verified":true,"asserted_confidence":0.7,"supports":0,"refutes":0,"corroborated":null}]}}