Testing Probabilistic Processes: Can Random Choices Be Unobservable?

Abstract: A central paradigm behind process semantics based on observability and testing is that the exact moment of occurring of an internal nondeterministic choice is unobservable. It is natural, therefore, for this property to hold when the internal choice is quantified with probabilities. However, ever since probabilities have been introduced in process semantics, it has been a challenge to preserve the unobservability of the random choice, while not violating the other laws of process theory and probability theory. This paper addresses this problem. It proposes two semantics for processes where the internal nondeterminism has been quantified with probabilities. The first one is based on the notion of testing, i.e. interaction between the process and its environment. The second one, the probabilistic ready trace semantics, is based on the notion of observability. Both are shown to coincide. They are also preserved under the standard operators.