{"work":{"id":"ebf5fa0e-3997-4dcc-922f-354e98be03dc","openalex_id":null,"doi":null,"arxiv_id":"2502.18770","raw_key":null,"title":"Reward shaping to mitigate reward hacking in rlhf","authors":null,"authors_text":"Jiayi Fu, Xuandong Zhao, Chengyuan Yao, Heng Wang, Qi Han, and Yanghua Xiao","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2502.18770","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-23T02:22:25.443620+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T06:35:39.131412+00:00","updated_at":"2026-05-23T02:22:25.443620+00:00","title_quality_ok":true,"display_title":"arXiv preprint arXiv:2502.18770 , year=","render_title":"arXiv preprint arXiv:2502.18770 , year="},"hub":{"state":{"work_id":"ebf5fa0e-3997-4dcc-922f-354e98be03dc","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":13,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2025-02-19T18:56:03+00:00","last_pith_cited_at":"2026-05-18T17:50:27+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":"2026-05-29T20:00:22.369087+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":[]}}