{"type": "article", "title": "Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/reward-granularity-in-rlvr-comparing-process-and-outcome-reward-structures-for", "original_source": "https://arxiv.org/abs/2607.02869", "published": "2026-07-07T04:00:00+00:00", "accessed": "2026-07-07", "id": "reward-granularity-in-rlvr-comparing-process-and-outcome-reward-structures-for"}