ECAI 2004 Conference Paper

[full paper]

Introducing Alias Information into Model-Based Debugging

Daniel Koeb, Franz Wotawa

Model-based diagnosis applied to computer programs has been studied for several years. Although there are still weaknesses in the used models, especially on dealing with dynamic data structures, the approach has been proven useful for automatic debugging. The weaknesses stem from the fact that heap objects are modeled without considering alias information. Our approach extends the modeling process with a static points-to analysis that reveals the structure and relations between heap objects. This points-to information is then used to improve existing value-based models for Java programs such that the diagnosis engine is able to differentiate between separate data structures. With this extension the set of diagnoses can be reduced for certain types of programs.

Keywords: Automatic Debugging, Diagnosis

Citation: Daniel Koeb, Franz Wotawa: Introducing Alias Information into Model-Based Debugging. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.833-837.