{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/f3513bfd-0efa-4d4d-b8dc-080f7224cee0\" width=\"1280\" height=\"720\" title=\"Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models — 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/f3513bfd-0efa-4d4d-b8dc-080f7224cee0/episode.poster.webp","title":"Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models","type":"video","version":"1.0","width":1280}