Recall of catastrophic errors on the test set as a function of the fraction of flagged predictions. Predictions are ranked by the predicted uncertainty (mLU) estimated from a DE (M = 5), and increasing fractions of the most uncertain predictions are flagged. Catastrophic errors are defined as predictions whose log-space error exceeds the 99th percentile (LAE₉₉ in Table 2). Fully-connected surrogates achieve higher recall at lower flagged fractions than latent-evolution models, indicating more effective uncertainty-based error detection.