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 demographic 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. We empirically demonstrate a Capacity Phase Transition: once linear shortcuts are pruned, networks are forced to utilize higher geometric capacity ($N \geq 16$) to curve the decision boundary and learn ethical representations. Our approach outperforms L1 Regularization -- which collapses into demographic bias -- and operates at a fraction of the computational cost of post-hoc methods like Just Train Twice (JTT), successfully reducing counterfactual gender vulnerability from 21.18\% to 7.66\%.

翻译：深度神经网络极易受到捷径学习的影响，频繁记忆低维虚假相关性而非内在因果机制，这不仅降低了分布外鲁棒性，还在敏感应用中导致严重的人口统计偏差。本文提出一种几何先验方法来缓解捷径学习。通过部署零隐藏层拓扑审计器，我们无需人工干预即可数学上分离出垄断梯度的特征。我们实证揭示了容量相变现象：一旦线性捷径被剪枝，网络被迫利用更高几何维度空间来弯曲决策边界并学习伦理表征。我们的方法优于L1正则化（该方法易陷入人口统计偏差），且计算成本仅为事后方法的一小部分，成功将反事实性别脆弱性从21.18%降至7.66%。