{"type":"link","version":"1.0","title":"Multiplying accuracy by reasoning-answer consistency punishes correct answers reached via inconsistent reasoning","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/reward-decomposition-accuracy-times-consistency-plus-format","thumbnail_url":"https://ai-arch.pages.dev/og/reward-decomposition-accuracy-times-consistency-plus-format.png","thumbnail_width":1200,"thumbnail_height":630}