Inspired by Valiant’s PAC learning model, the authors, using discretization techniques, seek a convergence of distribution-free expectations over classes of random variables. Real-valued functions (such as Glivenko-Cantelli classes) thus acquire a new uniformity. The model pioneers a simple combinatorial quantity generalized from the Vapnik-Chervonenkis dimension and implies learnability as a function of statistical regression. With learnability thus construed as probability, the accuracy parameter determines the complexity of the learner’s hypothesis class. Yet, can the authors’ refinements of quantitative elegance be transposed to pragmatic demonstrations?