Confidence-Weighted Plasticity: Experimental Validation and Boundary Conditions

We present experimental validation of Confidence-Weighted Plasticity (CWP), a mecha-nism for distributing gradient updates across modular components based on demonstratedpredictive reliability. Our experiments confirm that the core mechanism operates as spec-ified: confidence accurately tracks prediction accuracy, gradient routing scales accordingto plasticity, and the system responds to prediction failure. However, we identify a criticalboundary condition in tightly-coupled architectures where a component’s local predictiontask shares parameters with the global training objective. In such configurations, train-ing downstream components disrupts upstream predictions, triggering plasticity increaserather than protection—the mechanism actively directs more gradient toward the compo-nent we intend to protect. We characterise this limitation and discuss architectural require-ments for effective deployment.