# PhysioTRACE: Provenance-Aware Stress Tests for Physiological Foundation Models

arXiv: https://arxiv.org/abs/2609.34466 · HTML: https://mlsanity.com/paper/2609.34466/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 55 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 30 of 33)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [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)
- [Information-Theoretic Probing with Minimum Description Length](https://mlsanity.com/paper/2003.12298/) (2020)
- [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)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI](https://mlsanity.com/paper/2204.01075/) (2022)
- [A Theory of Usable Information Under Computational Constraints](https://mlsanity.com/paper/2002.10689/) (2020)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [ECG-FM: An Open Electrocardiogram Foundation Model](https://mlsanity.com/paper/2408.05178/) (2024)
- [MOABB: Trustworthy algorithm benchmarking for BCIs](https://mlsanity.com/paper/1805.06427/) (2018)
- [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)
- [Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06659/) (2024)
- [Causally motivated Shortcut Removal Using Auxiliary Labels](https://mlsanity.com/paper/2105.06422/) (2021)
- [Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations](https://mlsanity.com/paper/2107.00520/) (2021)
- [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)
- [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)
- [OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records](https://mlsanity.com/paper/2503.00711/) (2025)

## Abstract (arXiv)

Physiological foundation models encode how a signal was recorded alongside the physiology it reflects. When recording conditions are associated with diagnosis, this acquisition provenance can become a shortcut, yet the usual evidence, shifted transfer and provenance decodability, does not show whether a predictor uses it. We introduce PhysioTRACE, a four-axis behavioral audit for frozen encoders that separates what a probe can decode from what a fixed task head relies on. Recover scores how decodable provenance is; Stress reverses only the provenance-target association on the same held-out records; Intervene removes a train-localized provenance component; and Verify certifies that removal only if it beats matched random projections within a declared utility margin. Each audit thus ends in one of three verdicts: no reliance, or reliance with the remedy certified or refused. Across EEG and ECG, five training objectives, and five frozen foundation models, the relation between Recover's calibrated score and out-of-distribution utility changes sign between datasets, so neither can stand in for a reliance test. On paired EEG views where the shortcut is known by construction, the audit detects it (the exposed head loses about 0.2 AUROC when the association is reversed, while a control head is unaffected) and certifies removal of a rank-two component that restores control-level behavior without measurable utility loss, for both encoder objectives tested. On real ECG device metadata it returns all three verdicts: it certifies a remedy that removes 91% of one model's excess vulnerability, finds no reliance where device and diagnosis are barely associated, and refuses the remedy for a second model whose localized direction also carries task signal. Robustness to how inputs were recorded therefore needs a behavioral test, and PhysioTRACE provides one that can pass, fail, or refuse a remedy.