This paper is a work of fiction, but it is fiction with a very real purpose: to stimulate careful thought and friendly discussion about some questions for which thought is often careless and discussion is often unfriendly. To accomplish this purpose, the paper creates a fictional legal case. The most important issue in this fictional case is whether certain proffered expert testimony about software engineering for safetycritical systems should be admitted. Resolving this issue requires deciding the extent to which current practices and research in software engineering, especially for safety-critical systems, can rightly be considered based on knowledge, rather than opinion.

For any software system upon which lives depend, the most important question one can ask about it is, ‘How do we know the system is safe? ’ Despite the critical importance of this question, no widely accepted, generally applicable answer exists. Instead, debate continues to rage over the question, with theorists and practitioners quarrelling with each other and amongst themselves. This paper suggests a possible way forward towards quelling the quarrels, based on refining the critical safety question into additional questions, which may be more likely to have answers on which a consensus can be reached. 1