Yukitake Miyamoto

Rule Approximation and Nuisance Sensitivity in Finite-Sample GRU Learning

This preprint reports a controlled study of rule approximation and nuisance sensitivity in finite-sample GRU learning under a deterministic XOR target. Phase 1 contains eight training trajectories and 40 diagnostic readouts; six trajectories show decreasing rule-approximation err...

Information Location under Matched Predictive Opportunity

Model rankings are difficult to interpret when benchmark tasks differ both in how predictable the target is and in where the predictive signal is located. We construct a finite-support synthetic testbed with a known binary posterior and the same public semantic facts available to...