What question did this study set out to answer?

The aim is to establish a formal framework to assess the validity of AI models and mitigate risks associated with hallucinations.

February 11, 2026Open Access

Ontology-Preserving Mapping Theory (OPMT): A Homomorphic Framework for AI Safety and Model Auditing

Key Points

The aim is to establish a formal framework to assess the validity of AI models and mitigate risks associated with hallucinations.
Formalization of the Artsybashev Analysis Method (AAM-V1)
Implementation of the AAM-RSL v1.2 protocol
Definition of ontological homomorphism for mapping between reality and model
Classification of model outputs into VALID, FRINGE, and GHOST categories
Application of the framework in a case study using PseudoPhysicsAI
Detection of subtle violations of thermodynamic laws in AI outputs
Identification of areas where homomorphism is preserved or violated
Establishment of a rigorous auditing tool for high-responsibility domains

Abstract

As Large Language Models (LLMs) and generative AI systems become integral to Research & Development (R&D), the risk of "hallucinations" shifts from semantic incoherence to ontological invalidity — plausible but physically impossible descriptions. This paper formalizes the Artsybashev Analysis Method (AAM-V1) and the AAM-RSL v1.2 (Responsibility & Skepticism Layer) protocol. We introduce the concept of Ontological Homomorphism, a structural mapping Φ: R → M that preserves physical invariants (entropy, energy, causality) between reality (R) and the model (M). Model outputs are classified as VALID (homomorphism preserved), FRINGE (partial homomorphism with large kernel), and GHOST (structural violation). Using the PseudoPhysicsAI case study, we demonstrate how this framework detects subtle violations of thermodynamic laws, providing a rigorous tool for auditing AI in high-responsibility domains.

Read Full Paperexternally

KI fragen

Bookmark

View Full Paper