Reproduce “Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Xiaoyang Li, Zeyan Tao

The authors test whether EEG classifies five heard vowels for participants excluded from training, without listener-specific calibration. They audit event rows into independent consonant–vowel trials and compare 13 implementations using leave-one-subject-out testing and participant-level inference. Random Forest averages 21.474% balanced accuracy against 20% chance, but its interval spans chance and no model survives correction; evidence is limited to this protocol.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.