A credit-union lending desk must tell a member why a small-business loan was declined. One option is a short decision tree on five application fields; the other is a many-layer network with millions of internal weights. Which option creates the black-box explainability problem for testers and auditors?

A short decision tree on named fields can be inspected. A deep network with millions of weights is typically a black box for testers and auditors, especially in finance-like domains that need a reason. Calling the tree the black box, or claiming every decision is already explainable, misses that interpretability gap.