{"work":{"id":"74e3da93-f1b3-41df-bc52-f8092041fb58","openalex_id":null,"doi":null,"arxiv_id":"2404.07965","raw_key":null,"title":"Zhenghao Lin, Zhibin Gou, Yeyun Gong, Xiao Liu, Yelong Shen, Ruochen Xu, Chen Lin, Yujiu Yang, Jian Jiao, Nan Duan, and 1 others","authors":null,"authors_text":"Tokentune: Dual-level utility estimation for scalable data selection in instruction tuning","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2404.07965","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-03T08:17:45.470730+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T11:51:02.795704+00:00","updated_at":"2026-07-03T08:17:45.470730+00:00","title_quality_ok":false,"display_title":"Rho-1: Not all tokens are what you need","render_title":"Rho-1: Not all tokens are what you need"},"hub":{"state":{"work_id":"74e3da93-f1b3-41df-bc52-f8092041fb58","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2024-06-17T17:42:57+00:00","last_pith_cited_at":"2026-06-10T04:46:04+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":"2026-07-04T22:47:13.940373+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}