{"work":{"id":"0fa1ea01-03a1-4f54-b98a-d52862965176","openalex_id":"https://openalex.org/W4416138757","doi":"10.48550/arxiv.2506.05316","arxiv_id":"2506.05316","raw_key":null,"title":"Improving data efficiency for llm reinforcement fine-tuning through difficulty- targeted online data selection and rollout replay.arXiv preprint arXiv:2506.05316, 2025","authors":null,"authors_text":"Y","year":2025,"venue":"ArXiv.org","abstract":null,"external_url":"https://arxiv.org/abs/2506.05316","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":"2026-05-10T05:25:55.250589+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Improving data efficiency for llm reinforcement fine-tuning through difficulty-targeted online data selection and rollout replay.arXiv preprint arXiv:2506.05316","render_title":"Improving data efficiency for llm reinforcement fine-tuning through difficulty-targeted online data selection and rollout replay.arXiv preprint arXiv:2506.05316"},"hub":{"state":{"work_id":"0fa1ea01-03a1-4f54-b98a-d52862965176","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":17,"external_cited_by_count":0,"distinct_field_count":5,"first_pith_cited_at":"2026-02-02T11:24:36+00:00","last_pith_cited_at":"2026-06-25T15:31:23+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":"2026-08-22T18:49:46.905149+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"baseline","n":2}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"baseline","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}