15/09/2026
AI (MDPI) has published our work, "Architectural Transferability in Bounded AI: Five Conditions for Regulated Decision Domains." Available here: https://doi.org/10.3390/ai7090366
When does a bounded AI architecture proven in one regulated domain transfer to another — and when does it fail?
by George Melville, Dena Ghiassi, Scott Inthathirath and Julian Yeomans
Abstract:
AI and machine learning deployments in regulated decision contexts face an intolerance for inadmissible outputs (“hallucinations” when the model is generative) that current explainability methods address only after the fact. Bounded AI denotes prevention by architectural design. This study establishes five conditions (C1–C5) under which a bounded artificial intelligence (AI) architecture transfers from one regulated decision domain to another. Conditions C1 through C4 adapt or combine previously established principles. The most significant contribution is the discrete joint-state topology condition, C5, for which no precedent was found in this role. The claim is that these five conditions are jointly necessary for the closure property to survive an architectural transfer—while sufficiency is not claimed. Two of the five conditions are structural prerequisites governing whether the architecture’s operators can be constructed in a destination at all. The remaining three provide warrant conditions governing whether it is the appropriate instrument or not. In existing runtime-assurance architectures, the constraint acts after inference, on the output of the learned component. In contrast, the pattern developed in this paper reverses the assurance steps via a deterministic-first/learned-second approach. Namely, the assurance architecture acts before inference on the input domain: a deterministic filter admits only rule-compliant objects, and the trigger fires non-discretionarily on joint-state cell occupancy rather than on the learned score. The architecture’s domain-neutral type signatures are formalized, and three structural transfers are developed in depth: predictive maintenance, energy-grid management, and credit underwriting, each concluding with a closure proof.
Please read, review, comment, share, and download. We hope you find our open-access work useful.
AI and machine learning deployments in regulated decision contexts face an intolerance for inadmissible outputs (“hallucinations” when the model is generative) that current explainability methods address only after the fact. Bounded AI denotes prevention by architectural design. This study estab...
