{"work":{"id":"8c1a96bf-50f6-4e4a-b724-e61bee88277d","openalex_id":null,"doi":"10.48550/arxiv.2506.20920","arxiv_id":"2506.20920","raw_key":null,"title":"arXiv preprint arXiv:2506.20920 , year=","authors":null,"authors_text":"FineWeb2: One Pipeline to Scale Them All--Adapting Pre-Training Data Processing to Every Language , author=","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2506.20920","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-10T12:15:01.137692+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T17:50:08.473134+00:00","updated_at":"2026-07-10T12:15:01.137692+00:00","title_quality_ok":false,"display_title":"Fineweb2: One pipeline to scale them all -- adapting pre-training data processing to every language","render_title":"Fineweb2: One pipeline to scale them all -- adapting pre-training data processing to every language"},"hub":{"state":{"work_id":"8c1a96bf-50f6-4e4a-b724-e61bee88277d","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2025-08-08T17:21:06+00:00","last_pith_cited_at":"2026-06-26T13:03:29+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-07-08T20:32:48.905778+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}