{"work":{"id":"465cc66d-dd4e-459f-8514-738e42d0a154","openalex_id":null,"doi":null,"arxiv_id":"2402.16827","raw_key":null,"title":"arXiv preprint arXiv:2402.16827","authors":null,"authors_text":"Alon Albalak, Yanai Elazar, Sang Michael Xie, Shayne Longpre, Nathan Lambert, Xinyi Wang, Niklas Muennighoff, Bairu Hou, Liangming Pan, Haewon Jeong, et al","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2402.16827","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-23T19:08:20.886956+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T05:41:02.263605+00:00","updated_at":"2026-05-23T19:08:20.886956+00:00","title_quality_ok":false,"display_title":"A survey on data selection for language models","render_title":"A survey on data selection for language models"},"hub":{"state":{"work_id":"465cc66d-dd4e-459f-8514-738e42d0a154","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":17,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2024-02-29T13:53:35+00:00","last_pith_cited_at":"2026-05-21T12:21:41+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":"2026-05-25T22:05:57.743599+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":1},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}