Technical Spine

Local Validity Does Not Compose

A Theorem on the Limits of Bounded AI Audit

DemonstratedProof established in the rank-1 signed model. IncrementalDiagnostic available and validated; spectral experiment on 500 compositions consistent with the mechanism. Draft, April 2026.
Key result

No bounded-local audit can distinguish a coherent composition from one carrying k independent semantic obstructions; the coherence fee is the exact computable alternative

Falsification

Bounded-local method or low-order spectral statistic that certifies coherence on the semantic twins family

See the failure concretely

Three tools. Every pairwise check passes. The global cycle still fails — and Bulla locates the hidden obstruction from the schemas alone.

Open in the playground

Abstract

We prove that bounded-radius local audits and low-order spectral summaries cannot, in general, certify global semantic coherence of composed AI systems. We construct families of compositions (semantic twins) that are identical to every bounded local audit yet differ arbitrarily in a computable global obstruction. The proof uses high-girth graph families in a rank-1 signed model. We complement the impossibility with an exact online maintenance algorithm and a canonical benchmark family. Empirical validation on 500 synthetic compositions confirms spectral indistinguishability at scale.