<p>Paired statistical comparison of explanation faithfulness using per-image AUCs on the common subset (intersection by index, <i>n</i> = 369). We report the mean difference (MaxGRNet minus baseline model) and p-values from paired t-test and Wilcoxon signed-rank test. A positive indicates that MaxGRNet is better for Insertion and (1-Deletion). GaussianBlur baseline (k = 51, =8.0; 50 steps).</p>

Paired statistical comparison of explanation faithfulness using per-image AUCs on the common subset (intersection by index, n = 369). We report the mean difference (MaxGRNet minus baseline model) and p-values from paired t-test and Wilcoxon signed-rank test. A positive indicates that MaxGRNet is better for Insertion and (1-Deletion). GaussianBlur baseline (k = 51, =8.0; 50 steps).