{"work":{"id":"00edb0c5-3c62-421d-a532-03e2594f1dba","openalex_id":null,"doi":null,"arxiv_id":"2502.17387","raw_key":"raw:3a6d6d8782ec3170fb046336","title":"Big-math: A large-scale, high-quality math dataset for reinforcement learning in language models.arXiv preprint arXiv:2502.17387,","authors":null,"authors_text":"Alon Albalak, Duy Phung, Nathan Lile, Rafael Rafailov, Kanishk Gandhi, Louis Castricato, Anikait Singh, Chase Blagden, Violet Xiang, Dakota Mahan, et al","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2502.17387","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T16:39:58.415508+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T08:22:37.575600+00:00","updated_at":"2026-07-04T16:39:58.415508+00:00","title_quality_ok":true,"display_title":"Big-math: A large-scale, high-quality math dataset for reinforcement learning in language models","render_title":"Big-math: A large-scale, high-quality math dataset for reinforcement learning in language models"},"hub":{"state":{"work_id":"00edb0c5-3c62-421d-a532-03e2594f1dba","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":21,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2025-04-15T17:59:51+00:00","last_pith_cited_at":"2026-06-30T20:28:08+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":"2026-08-21T10:19:45.196672+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"dataset","n":2}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"use_dataset","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}