Critical observations in model-based diagnosis

In this paper, we address the problem of finding the part of the observations that is useful for the diagnosis. We define a sub-observation as an abstraction of the observations. We then argue that a sub-observation is sufficient if it allows a diagnoser to derive the same minimal diagnosis as the original observations; and we define critical observations as a maximally abstracted sufficient sub-observation. We show how to compute a critical observation, and discuss a number of algorithmic improvements that also shed light on the theory of critical observations. Finally, we illustrate this framework on both state-based and event-based observations.