Epistemic limits of local interpretability in self-modulating cognitive architectures.

ABSTRACT:

Introduction

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.

Methods

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).

Results

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

SUBMITTER: Mahrouk A 

PROVIDER: S-EPMC12702970 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature