Fig. 7From: Uncertain of uncertainties? A comparison of uncertainty quantification metrics for chemical data setsError-based calibration plots for the LS-GCN uncertainties based on a GCNN model with a 9k+1k training set consisting of Crippen’s logP training data as well as the GCNN model trained on 145k+5k samples. Each bin contains 250 of the test samples. a GCN10k \(\rho _{rank}=-0.02\) b GCN150k \(\rho _{rank}=0.23\)Back to article page