{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":480,"html":"<iframe src=\"https://montaan.com/embed/episode/a5ee5884-f1f9-42ed-ba83-5bdd6f7c7b8d\" width=\"1280\" height=\"480\" title=\"Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned 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/a5ee5884-f1f9-42ed-ba83-5bdd6f7c7b8d/episode.poster.webp","title":"Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models","type":"rich","version":"1.0","width":1280}