“…Note that in both the EMA and the FDA guidelines rejecting outliers is addressed in the context of another metric, specificity, and is not further discussed here. Moreover, within the broader context of the increasing efforts toward continuous manufacturing, robustness of a model can be also associated with obtaining good predictions for a prolonged period of time, i.e., increasing up-time of a model . Although this idea of prolonging model applicability extends the concept of robustness to include the time dimension, it does not touch upon the definition of robustness at the time of model creation, and thus, it is not further discussed here.…”