This paper considers the training of logical (Boolean) capabilities with concentrate on the generalization on the unseen (GOTU) setting, a powerful case of out-of-distribution generalization. That is motivated by the truth that the wealthy combinatorial nature of information in sure reasoning duties (e.g., arithmetic/logic) makes consultant information sampling difficult, and studying efficiently below GOTU offers a primary vignette of an ‚extrapolating‘ or ‚reasoning‘ learner. We then examine how totally different community architectures educated by (S)GD carry out below GOTU and supply each theoretical and experimental proof that for a category of community fashions together with cases of Transformers, random options fashions, and diagonal linear networks, a min-degree-interpolator (MDI) is realized on the unseen. We additionally present proof that different cases with bigger studying charges or mean-field networks attain leaky MDIs. These findings result in two implications: (1) we offer a proof to the size generalization drawback (e.g., Anil et al. 2022); (2) we introduce a curriculum studying algorithm known as Diploma-Curriculum that learns monomials extra effectively by incrementing helps.