Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control

ArXi:2604.22413v1 Announce Type: cross Graph Transformers can mix information globally, but this flexibility also creates failure modes: some tasks require long-range communication while others are better served by local interaction. We study this through a synthetic node-classification benchmark on contextual stochastic block model graphs, where labels are generated by a controllable mixture of local and far-shell signals. We define distance-misaligned