Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts

arXiv:2608.11212v1 Announce Type: new Abstract: Topk MixtureofExperts MoE routing is discontinuous, so a deploymentmotivated numerical disturbance simulated 4bit KVcache quantization read by a protected BF16 gate pushes tokens across decision boundaries and flips which experts fire.