{"type":"link","version":"1.0","title":"Mine vertical pretraining corpora from Common Crawl with an iterative seed-and-classify pipeline","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/biz-iterative-classifier-domain-corpus-mining-service","thumbnail_url":"https://ai-arch.pages.dev/og/biz-iterative-classifier-domain-corpus-mining-service.png","thumbnail_width":1200,"thumbnail_height":630}