{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","url":"https://codeofpaper.com/paper/2603.03291","arxiv_url":"https://arxiv.org/abs/2603.03291","published":"2026-02-06","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}