Process models are important artifacts to support organizations in documenting, understanding and monitoring their business. Over time, these process models may become outdated and need to be revised to again accurately describe the business, its culture and regulations. Process model repair techniques help at automatically revising the existing model from behavior traced in event logs. So far, such techniques have focused on identifying which parts of the model to change and how to change them, but they tend to overlook the potential of using knowledge from practitioners to inform the revision. Theory revision techniques are able to revise a logical theory using data. They allow the practitioner to specify which part of the theory is kept unchanged during the revision and which part of the data should or should not be explained by the theory. This paper dives into first ideas on how process model repair techniques can benefit from theory revision. In particular, it elaborates on the use of domain knowledge to identify which data are relevant to be considered and which parts of the model are indeed changeable. Finally, this paper analyzes existing process model repair techniques and discusses challenges that need to be addressed in order to exploit theory revision.