Preprint quantifies proteomics data leakage: no real signal still yields AUCs near 0.8
bttyeo · x · 2026-09-11
A new preprint quantifies a common cause of irreproducible proteomics biomarker studies: data leakage. Working with Jake Vogel, Caitlin Finney, and others, the authors show that with no true signal at all, runs containing data leakage can still reach AUCs near 0.8 — deceptively strong performance from pure noise. A methodological warning for biomedical machine learning research.
Related event: Preprint Quantifies Data Leakage: Near-0.8 AUC With No Signal(2 posts)→
More from Research
- Google brings 41 accepted papers to ECCV 2026, from video spatial understanding to TIPSv2 — ymatias · 2026-09-11
- OpenAI's internal model claims a Navier-Stokes millennium prize proof, says analyst — QuintinPope5 · 2026-09-11
- AI-mapped fruit fly brain (166,000+ neurons) now plays Super Smash Bros Melee on a Mac Studio — TheMoonMidas · 2026-09-11
- IBM open-sources Steerability toolkit with steering pipelines and vLLM-Hook plugin — krvarshney · 2026-09-11
- Researchers recover encrypted chain-of-thought from Claude, OpenAI and Google APIs in two calls — Miles_Brundage · 2026-09-11
- DARPA launches expMath program; researchers share AI-driven mathematical discovery work — wellecks · 2026-09-11