# A Negative-Control Protocol for Clinical EEG Foundation-Model Benchmarks: Dataset Identity and External-Cohort Stress Testing

arXiv: https://arxiv.org/abs/2607.24519 · HTML: https://mlsanity.com/paper/2607.24519/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024)
- [REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects](https://mlsanity.com/paper/2510.21585/) (2025)
- [Transfer Learning in Brain-Computer Interfaces](https://mlsanity.com/paper/1512.00296/) (2015)
- [EEG Foundation Models: A Critical Review of Current Progress and Future Directions](https://mlsanity.com/paper/2507.11783/) (2025)
- [EEGMamba: Bidirectional State Space Model with Mixture of Experts for EEG Multi-task Classification](https://mlsanity.com/paper/2407.20254/) (2024)
- [AdaBrain-Bench: Benchmarking Brain Foundation Models for Brain-Computer Interface Applications](https://mlsanity.com/paper/2507.09882/) (2025)
- [EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications](https://mlsanity.com/paper/2512.08959/) (2025)
- [OmniEEG-Bench: A Standardized Evaluation Benchmark for EEG Foundation Models](https://mlsanity.com/paper/2606.00815/) (2026)
- [NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces](https://mlsanity.com/paper/2605.14698/) (2026)
- [Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models](https://mlsanity.com/paper/2605.17562/) (2026)
- [EEG-FM-Audit: A Systematic Evaluation and Analysis Pipeline for EEG Foundation Models](https://mlsanity.com/paper/2605.26910/) (2026)
- [Cross-Cohort Spectral-Temporal Dissociation in Frozen EEG Foundation-Model Representations](https://mlsanity.com/paper/2607.24834/) (2026)

## Built on by (most cited first, 4 of 4)

- [Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions](https://mlsanity.com/paper/2607.28687/) (2026)
- [Matched-Input Estimates Differ in Sign Across Architectures: Auditing EEG Foundation Models on Motor Imagery](https://mlsanity.com/paper/2609.23924/) (2026)
- [Representational and Functional Robustness to Electrode Montages in EEG Foundation Models](https://mlsanity.com/paper/2609.36288/) (2026)
- [Dataset-Specific Encoding of Image Content Underlies Cross-Dataset Failure in Brain MRI Foundation Models](https://mlsanity.com/paper/2610.13027/) (2026)

## Abstract (arXiv)

EEG foundation-model gains may depend on cohort, montage, or probe design. We evaluated five models on five tasks across four benchmark datasets plus Korean CAUEEG, using subject-disjoint validation where identifiers exist. CAUEEG is recording-level with an annotated no-overlap held-out sensitivity. On matched CAUEEG normal/mild cognitive impairment/dementia classification (1,187 recordings), classical features reached 0.734 macro-AUROC (enhanced sensitivity: 0.736), versus BIOT-bipolar16 0.677, CBraMod 0.669, and REVE 0.568. The annotated no-overlap held-out subset preserved the classical-over-REVE ordering (0.717 versus 0.565). All five encoders decoded dataset identity at 1.000 before and after in-fold PCA-50; label permutations collapsed to chance and balanced subsamples remained at 1.000. This establishes dataset membership, not a causal site, geography, or population effect. A matched fully randomly initialized encoder was descriptively higher than pretrained REVE on CAUEEG (0.667 versus 0.570), and correct- versus scrambled-source-label LoRA runs yielded numerically similar AUROCs in unmatched descriptive sensitivities, not label-effect estimates or equivalence tests. On CHB-MIT cross-subject ictal detection, REVE reached 0.793 AUROC, versus 0.739 for the best tested enhanced nonlinear comparator, 0.691 for fully random initialization, and 0.505 for raw-signal random features. The paired REVE-minus-enhanced-comparator difference was +5.38 percentage points (95% CI -0.36 to +11.22), so comparator superiority remains unresolved; an amplitude-aware comparator also cannot be reconstructed from the retained normalized inputs. We distill montage matching, patient-overlap checks, stronger comparators, and representation controls into a reporting protocol for clinical EEG foundation-model studies.