Pretraining leaves a spectral fingerprint in the weights: after conditioning on architecture and strategy, one spectral statistic ranks OOD robustness across 116 foundation models without target data
The work reads pretrained-weight spectral structure through 15 (architecture x pretraining-strategy) cells, proves that the OOD accuracy gap is bounded by how tightly source representations concentrate, and shows that a single statistic selected per cell orders OOD robustness across 116 models and 7 modalities, with the cell, metric and sign locked before evaluation for out-of-matrix families including EEG, genomic and protein.