Explainable artificial intelligence (XAI), the goodness criteria and the grasp-ability test

This addresses the need for better evaluation metrics in explainable AI for users, but it appears incremental as it proposes a new test without demonstrated broad impact.

The paper tackles the problem of evaluating explanations in explainable AI by introducing the 'grasp-ability test' as a goodness criterion to compare which explanations are more meaningful for users to understand algorithmic data processing, but it does not provide concrete results or numbers.