{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/da240949-4068-49c2-94e1-f8257d0f8d93\" width=\"1280\" height=\"720\" title=\"Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLMs — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://montaan.com/","thumbnail_url":"https://montaan.com/media/episodes/da240949-4068-49c2-94e1-f8257d0f8d93/episode.poster.webp","title":"Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLMs","type":"video","version":"1.0","width":1280}