Site Is Decodable Before Pretraining: Negative Controls for Probing Frozen Brain-MRI Foundation Models

Excerpt

arXiv:2608.10295v2 Announce Type: replace-cross Abstract: Brain foundation models are often tested with a probe. The model is frozen, a simple classifier is trained on its output, and the classifier's accuracy is taken as a sign of what pretraining learned. We show that this reading can be wrong unless two controls are reported with it. We probed three frozen 3-D brain-MRI models at five depths, on two independent multi-site cohorts (ABIDE-I and ABIDE-II). The site where a scan was acquired coul