{"work":{"id":"f038029e-5113-4f29-9db3-7e5d6144e95f","openalex_id":"https://openalex.org/W4389469774","doi":"10.48550/arxiv.2312.02406","arxiv_id":"2312.02406","raw_key":null,"title":"Efficient online data mixing for language model pre-training.arXiv preprint arXiv:2312.02406,","authors":null,"authors_text":"Alon Albalak, Liangming Pan, Colin Raffel, and William Yang Wang","year":2023,"venue":"arXiv (Cornell University)","abstract":null,"external_url":"https://arxiv.org/abs/2312.02406","cited_by_count":0,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-13T20:08:12.633068+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Efficient online data mixing for language model pre-training","render_title":"Efficient online data mixing for language model pre-training"},"hub":{"state":{"tier_text":"hub","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":0},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}