What question did this study set out to answer?

The aim is to present a governed intelligence framework that enhances the safety and verifiability of AI systems.

May 10, 2026Open Access

Governed Intelligence: A Spectral Framework for Verifiable AI Accords and Structural Security

Key Points

The aim is to present a governed intelligence framework that enhances the safety and verifiability of AI systems.
Separated AI proposal engine from execution gate to enforce safety regulations.
Implemented a control-theoretic observer-augmented safety filter to ensure zero false negatives under degradation.
Developed a reinforcement learning safety grid that significantly reduces violations compared to traditional methods.
Achieved zero false negatives in the observer-augmented safety filter even with sensor degradation.
The spectral-trajectory gate reduced catastrophic violations by 98% compared to payload-only filters.

Abstract

Abstract We present a governed intelligence architecture that separates an AI agent’s proposal engine (Ghost) from a hard execution gate (Hermes) to enforce structural accords and security invariants. The system’s safety is verified through a novel spectral structural operator K(H) = λ1:k L(H) that extracts the leading eigenvalues of the normalized graph Laplacian of the embedding space. This operator converts representational collapse from a metaphor into a differentiable, measurable quantity. We provebthe operator’s utility through two experiments: (1) a control-theoretic observer-augmented safety filter (VECTOR) that achieves zero false negatives under sensor degradation, and (2) a reinforcement learning safety grid (SafetyGrid DSE) where a spectral-trajectory gate reduces catastrophic violations by 98% compared to payload-only filters. The framework is formalized as a Whitebox AI safety paradigm, where internal state is instrumented and structural invariants are continuously monitored.

Ask AI

Helpful

Bookmark

View Full Paper