a novel and scalable method for inferring a continuous target as well as representations for epistemic and aleatoric

We thank the reviewers for their very constructive and detailed feedback on our manuscript. "Confused evidence": As R1 correctly states, the regularizer captures scenarios where the evidence However, we do not believe that the approach "conflates Further details and analysis are added to the manuscript. AUC: The histograms (and CDFs) provided in Figs. 5, 6, and S5 (as in [21], [Nalisnick, E. et al. '18], and others) are richer performance statistics and directly reduce to the requested To address these concerns, we have added all AUC-ROC values to our performance charts. Adversarial: We updated the implementation details of the attack method (FGSM). R2: 1. Figure 1 aleatoric: Within the training region there are very few differences, which can be attributed to intrisinic OOD there is much more variability, aligning with MVE [18, 28].