{"id":777,"slug":"ruggsea--infini-news-corpus","name":"infini-news-corpus","author":"ruggsea","description":"\n\t\n\t\t\n\t\n\t\n\t\tINFINI-NEWS Corpus\n\t\n\n\n🔎 Search this corpus online: query it with sub-second full-text search and n-gram counts — in the browser or via a public, keyless REST API, no download required — at infini-news.uni-graz.at (API reference).\n\nA multilingual news corpus extracted from\nCommon Crawl CC-News WARC files.\nOne row per article, with body text extracted via\ntrafilatura,\nWARC provenance, and derived metadata (publish date, language, topic,\nbyte hashes) in a single flat schema. Covers… See the full description on the dataset page: https://huggingface.co/datasets/ruggsea/infini-news-corpus.","tags":"[\"Task_categories:text-Generation\",\"Task_categories:text-Classification\",\"Task_categories:text-Retrieval\",\"Annotations_creators:machine-Generated\",\"Multilinguality:multilingual\",\"Source_datasets:original\"]","license":null,"framework":null,"parameters":null,"downloads":56412,"likes":31,"verified":0,"created_at":"2026-08-03 12:23:29","updated_at":"2026-08-03 15:23:32","source_url":"https://huggingface.co/datasets/ruggsea/infini-news-corpus","source_platform":"huggingface","hf_repo_id":"ruggsea/infini-news-corpus","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":776,"model_id":777,"version":"v1.0.0","manifest_hash":"d372459749891293e6e1b301405494657f984bbb57bda26012a1cda92dfecfd9","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/ruggsea--infini-news-corpus/v1.0.0.json","created_at":"2026-08-03 12:23:29"}],"files":[],"signatures":[{"id":1349,"version_id":776,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"9c163b3b9ef4edba3896dfa9d60869058d809babaeedcd9cebcbe2b2bbcf0cc2","attestation_type":"registry","signed_at":"2026-08-03 12:23:29"}],"hndl":null}