A probabilistic model of belief in safety cases

A safety case is a hierarchical argument supported by evidence, whose scope defined contextual information. The goal to show that the conclusion of such argument, typically “the system acceptably safe”, true. However, because knowledge about systems always imperfect, value true cannot be assigned with absolute certainty. Instead, researchers have proposed assess belief true, which should high for safe system. Existing methods calculations were shown suffer from various limitations lead unrealistic values. This paper presents novel method, underlined formal definitions concepts as being or context defining scope. Given these definitions, general, probabilistic model calculation in an arbitrary derived. Because derived independent any safety-case notation, elements commonly used notation are mapped and corresponding represented Bayesian Network enable large-scale calculations. Finally, method applied scenarios where previous produce values, it presented produces values expected.