Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning

ArXi:2604.11704v1 Announce Type: cross Deep Neural Networks are highly susceptible to shortcut learning, frequently memorizing low-dimensional spurious correlations instead of underlying causal mechanisms. This phenomenon not only degrades out-of-distribution robustness but also induces severe graphic biases in sensitive applications. In this paper, we propose a geometric \textit{a priori} methodology to mitigate shortcut learning. By deploying a zero-hidden-layer ($N=1$) Topological Auditor, we mathematically isolate features that monopolize the gradient without human intervention.