{"data":{"slug":"c4","etype":"dataset","name":"C4","cat":"Web Corpus","subtitle":"Google's cleaned Common Crawl — the reproducible baseline.","summary":"The Colossal Clean Crawled Corpus (2019, for T5) applied documented filters to Common Crawl and released the recipe, becoming the standard public pre-training baseline and the corpus of record for studying what models actually read.","attrs":null,"kf":null,"aliases":["Colossal Clean Crawled Corpus"],"ticker":null,"exchange":null,"hq":null,"founded":null,"website":null,"status":null,"region":null,"asof":"2026-01-15","sources":[{"url":"https://www.tensorflow.org/datasets/catalog/c4","label":"C4 (TensorFlow Datasets)"}]},"meta":{"found":true,"count":1,"served_from":"site cache (no live upstream calls)","as_of":"2026-10-14T02:47:34+00:00","disclaimer":"Research and information only — not investment advice. Structured records carry basis labels (vendor spec / reported / estimate); market quotes are delayed/indicative.","attribution":"Records compiled from vendor documentation, official filings and reputable public reporting; market quotes via financial data providers. See /data-sources."}}