In this work, we propose a new representation for molecules that overcomes those limitations.

The model proposed here enables proper uncertainty quantification of the causal effects thus allowing the definition of optimal experimental design strategies.

The reviewers2 acknowledge that the ideas presented inthe paper are compelling, sound and appear tobeeffective(R3), offering a3 great add to the GP literature (R1) which is also supported by a solid and an interesting theoretical foundation (R2,4 R4). Existing multi-output GP models are not applicable to our setting (see line 79-83) and are thus not16 comparabletotheDAG-GPmodel. Wehavefurther clarified this point in Section 1.2.

Our paper adopts the CP decomposition because it handles heterogeneity in each mode, learns the clustering patterns across different modes of data in amore independent way, and provides flexibility for clustering a certain mode of the tensor without being affected by correlation with other modes. Our method is similar to those in a recent series of papers [27, 21] that use the CP decomposition structure. Note that their estimation algorithms use the framework oftensor power method [1].

Calibrated probabilistic classifiers are models whose predicted probabilities can directly be interpreted as uncertainty estimates. It has been shown recently that deep neural networks arepoorly calibratedandtend tooutput overconfident predictions.