# The Identity Trap in EEG Foundation Models: A Diagnostic Audit arXiv: https://arxiv.org/abs/2606.06647 ยท HTML: https://mlsanity.com/paper/2606.06647/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Builds on 25 of its 54 references that are in the map. - First posted on arXiv 4 Jun 2026. ## Builds on (most cited first, 25 of 25) - [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020) - [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014) - [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016) - [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024) - [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023) - [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022) - [BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data](https://mlsanity.com/paper/2101.12037/) (2021) - [CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2412.07236/) (2024) - [A mathematical theory of semantic development in deep neural networks](https://mlsanity.com/paper/1810.10531/) (2018) - [Uncovering the structure of clinical EEG signals with self-supervised learning](https://mlsanity.com/paper/2007.16104/) (2020) - [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) - [EEG Foundation Models: A Critical Review of Current Progress and Future Directions](https://mlsanity.com/paper/2507.11783/) (2025) - [EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models](https://mlsanity.com/paper/2508.17742/) (2025) - [Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective](https://mlsanity.com/paper/2405.16747/) (2024) - [Parameter Efficient Fine-tuning via Explained Variance Adaptation](https://mlsanity.com/paper/2410.07170/) (2024) - [AdaBrain-Bench: Benchmarking Brain Foundation Models for Brain-Computer Interface Applications](https://mlsanity.com/paper/2507.09882/) (2025) - [Demixed principal component analysis of population activity in higher cortical areas reveals independent representation of task parameters](https://mlsanity.com/paper/1410.6031/) (2014) - [EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications](https://mlsanity.com/paper/2512.08959/) (2025) - [EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decoding](https://mlsanity.com/paper/2506.19141/) (2025) - [Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal](https://mlsanity.com/paper/2602.11558/) (2026) - [Mitigating Subject Dependency in EEG Decoding with Subject-Specific Low-Rank Adapters](https://mlsanity.com/paper/2510.08059/) (2025) - [EEG fingerprinting: subject specific signature based on the aperiodic component of power spectrum](https://mlsanity.com/paper/2001.09424/) (2020) - [What Do EEG Foundation Models Capture from Human Brain Signals?](https://mlsanity.com/paper/2605.11410/) (2026) - [From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data](https://mlsanity.com/paper/2505.23042/) (2025) - [SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels](https://mlsanity.com/paper/2602.17251/) (2026) ## Built on by (most cited first, 2 of 2) - [Cross-Cohort Spectral-Temporal Dissociation in Frozen EEG Foundation-Model Representations](https://mlsanity.com/paper/2607.24834/) (2026) - [Separating personal from population gains when calibrating EEG foundation models for new users](https://mlsanity.com/paper/2609.34801/) (2026) ## Abstract (arXiv) Objective. EEG foundation models (FMs) report strong accuracy on clinical resting-state EEG. However, high accuracy under subject-disjoint cross-validation remains ambiguous: it can reflect a genuine clinical biomarker, or subject-identity features that correlate with the label. We name this the Identity Trap and ask whether it can be diagnosed at the representation level before fine-tuning. Approach. We propose FMScope, a frozen-representation protocol packaging five diagnostics: variance decomposition, subject-axis erasure, aperiodic 1/f ablation, layer-wise label probing, and within-subject direction consistency. We apply it to three pretrained FMs (LaBraM, CBraMod, REVE) across four datasets in a 2x2 layout: subject relation of label x presence of a consensus cross-subject EEG marker. Main results. (i) The Identity Trap is universal: frozen subject-variance is 13-89x a random null in 12/12 pairs, rising in all 12 under fine-tuning (+10 to +63 pp). This dominance is a removable linear axis: erasing it improves label decoding where the label varies within subject (+6 to +12 pp in primary cells; +4 to +27 pp across external cohorts). (ii) Aperiodic 1/f is one subject carrier: removing it drops the subject probe by 9-19 pp on LaBraM and CBraMod. REVE saturates subject identity without measurable aperiodic dependence. (iii) Fine-tuning amplifies label-variance only in cells with a literature-established cross-subject marker. Significance. The Identity Trap is a physically-grounded instance of shortcut learning: the preferred cue has a measurable physiological component, and subject-disjoint splitting alone cannot rule it out. FMScope separates gains reflecting a biological marker from those reflecting subject identity.