NOETHER: A Constructive Framework for Metamorphic Pattern Discovery from Operator Algebras

2026-05-17

AI Summary

This work addresses three fundamental challenges in metamorphic testing—namely, the origin, closure, and transferability of metamorphic relations (MRs)—by introducing the NOETHER framework. NOETHER combines an upstream eight-module decomposition grounded in operator algebra (encompassing symmetry, order structure, self-adjointness, and related properties) with a downstream CONSTRUCT-MP algorithm to automatically derive a set of MetaPatterns from programs. These MetaPatterns enjoy algebraic closure and polynomial-time decidability, elevating MR induction to a domain-level algebraic abstraction and enabling a deductive, mechanized approach to MR generation. For the first time, this method provides formal theoretical guarantees for both closure and decidability. Empirical validation across reactor physics, equivariant machine learning, and relational query optimization demonstrates systematic reconstruction of known MRs, synthesis of executable MRs, and verification of core predictions, while counterexamples refute the conjecture of absolute completeness and reveal five dimensions for extending the Translate framework.

Abstract

Context. Metamorphic Testing is recognised in IEEE/ISO software-testing standards and increasingly recommended for AI systems, but its progress is bottlenecked by metamorphic relation (MR) identification: existing approaches (structured frameworks, mining and evolutionary pipelines, LLM-assisted methods, MetaPattern catalogues) share an inductive grounding that leaves three foundational questions open: origin, closure, and transferability. Objective. We propose a framework whose downstream step from program-induced operator algebra to MetaPattern set is mechanical and provable, while the upstream curation of the algebra is a stated empirical hypothesis with explicit scope precondition. Method. NOETHER is a two-layer framework. The upstream layer is an eight-block decomposition over recurrent mathematical structures (symmetry, order, self-adjoint, time-reversal, limit, qualitative-dynamics, method-comparison, relational equivalence). The downstream CONSTRUCT-MP algorithm produces a MetaPattern set with algebraic-closure (Theorem 1) and polynomial-time decidability (Theorem 2) guarantees. We test the framework on three operator-algebraic domains. Results. On Boltzmann reactor physics NOETHER systematises a prior inductive catalogue; on equivariant ML it derives executable MRs for rotation invariance, adjoint duality, and training-trajectory reversibility; on relational query optimisers it exercises the relational-equivalence block. The central falsifiable prediction (L*-blindness on homogeneity-preserving mutators) holds on the in-scope substrate. The absolute-completeness conjecture (Theorem 1') is falsified on PWR core diffusion via two pairwise-independent counterexamples that identify five Translate-extension dimensions. Conclusion. Induction is relocated from per-program MR sampling to a per-domain algebraic layer; the downstream step is deductive and mechanical.

Problem

• metamorphic testing
• metamorphic relation
• operator algebras
• inductive grounding
• transferability

Innovation

• Metamorphic Testing
• Operator Algebras
• Constructive Framework
• Algebraic Closure
• MetaPattern Discovery