← All research papers
Published

Common-Cause Failures in Physical AI: Estimating β-Coefficients for Redundant Safety Architectures

Author
Mati Melchior · Independent Physical AI Safety Researcher
Published
2026-05-15
Licence
CC BY 4.0

Abstract

Physical AI systems commonly claim 'redundant' or 'dual-channel' safety architectures. Per IEC 61508-6 Annex D, the efficacy of redundancy depends on the β-coefficient: the fraction of channel failures that are common-cause. A redundancy claim without β disclosure is therefore unverifiable. This paper presents a methodology for estimating β from publicly available architecture information, applied to five anonymized Physical AI architectures and a wider survey of approximately 30 cases. Most claimed-redundant architectures show estimated β > 5%, with software-only configurations approaching 100% for operating-system-level common-cause failures. We provide a 12-question evaluator's checklist…

Keywords Physical AI Safety · common-cause failure · β-coefficient · IEC 61508 · redundancy · fault-tolerance

Cite as

Mati Melchior (2026). Common-Cause Failures in Physical AI: Estimating β-Coefficients for Redundant Safety Architectures. Physical AI Safety Press. https://doi.org/10.5281/zenodo.20048924

We use cookies

This site uses essential cookies to function and, with your consent, analytics cookies (Google Analytics) to understand how the site is used. Learn more.