straints probabilistically, i.e. the challenge is to incorporate constraints in a model that infers output distributions

We thank all reviewers for their insightful comments. "repulsive/diverse functions" also makes it more likely to violate a constraint; for example, Figure S1 below shows that (instead of 50). We acknowledge points about similarity to [18] made by R4. Equation (1) in Definition 4.2 should read: