An AI agent audited medical-imaging papers and found widespread leakage
wandedob · x · 2026-07-27
To learn Claude Cowork, the author built an AI agent that searches for papers using 2D models on 3D medical volumes and checks whether each study used patient-wise splits or leaky slice/image-wise splits.
The agent-based review found the results “pretty depressing,” suggesting the data-leakage problem is still widespread in this niche.
Related event: Developer Builds AI Agent to Audit Medical Imaging Papers for Data Leakage(2 posts)→
More from coding & agent
- Codex gets mocked for serializing eight parallel jobs into an eight-hour loop — chaumian · 2026-07-27
- Cached input makes looped agent workflows cheaper than they look — yunta_tsai · 2026-07-27
- A new agent framework reaches 85% on ARC-AGI3 public games — JFPuget · 2026-07-27
- Session promises best practices for building cross-platform mobile apps with coding agents — TheOyinbooke · 2026-07-27
- Opinion: Stop Overengineering Your AI Agent Harnesses — rseroter · 2026-07-27
- A 1996 book predicted the AI coding workflow nearly 25 years early — chaitjo · 2026-07-27