Epistemic limits of local interpretability in self-modulating cognitive architectures

Local interpretability methods such as LIME and SHAP are widely used to explain model decisions. However, they rely on assumptions of local continuity that often fail in recursive, self-modulating cognitive architectures.

We analyze the limitations of local proxy models through formal reasoning, simulation experiments, and epistemological framing. We introduce constructs such as Modular Cognitive Attention (MCA), the Cognitive Leap Operator (Ψ), and the Internal Narrative Generator (ING).

Our findings show that local perturbations yield divergent interpretive outcomes depending on internal cognitive states. Narrative coherence emerges from recursive policy dynamics, and traditional attribution methods fail to capture bifurcation points in decision space.

We argue for a shift from post-hoc local approximations to embedded narrative-based interpretability. This reframing supports epistemic transparency in future AGI systems and aligns with cognitive theories of understanding.