{"work":{"id":"e40578ea-e2a1-4ab3-a681-c6ee0356fb90","openalex_id":null,"doi":null,"arxiv_id":"2603.23871","raw_key":null,"title":"Hdpo: Hybrid distillation policy optimization via privileged self-distillation.arXiv preprint arXiv:2603.23871, 2026","authors":null,"authors_text":"Ken Ding","year":2026,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2603.23871","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-02T11:56:55.321611+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T11:11:06.460357+00:00","updated_at":"2026-07-02T11:56:55.321611+00:00","title_quality_ok":true,"display_title":"Hdpo: Hybrid distillation policy optimization via privileged self-distillation","render_title":"Hdpo: Hybrid distillation policy optimization via privileged self-distillation"},"hub":{"state":{"work_id":"e40578ea-e2a1-4ab3-a681-c6ee0356fb90","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":"2026-04-14T17:54:28+00:00","last_pith_cited_at":"2026-06-04T11:13:01+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":"2026-07-02T18:52:52.349657+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}