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
- ParetoRSI-Gym benchmarks whether AI agents can recursively self-improve LLMs across domains — Haojin Wang · 2026-10-28
- Stanford's Ψ-0.6 is a unified vision-language world model with adaptive reasoning streams — Stanford · 2026-10-28
- Shanghai AI Lab's OpenESM shows energy-steered models can scale as foundation learners — Shanghai-AI-Laboratory · 2026-10-28
- CellTrack-Bench tests VLMs on microscopic cell tracking, exposing reasoning gaps — biohub · 2026-10-28
- Hybrid LLM agent scores 83.2%, beats nine VLA policies on new SO-101 robot arm benchmark — Truman Hickok · 2026-10-28
- DeepMind researcher: all of mathematics will soon be formalizable, with agents hunting proofs — ChrSzegedy · 2026-10-28