When Fairness Fails in Groups: From Lone Counterexamples to Discrimination Clusters
Imagine two fairness bugs. In the first, changing a protected attribute while holding everything else constant shifts a model’s output enough to trigger one unfair decision. In the second, the same underlying applicant profile can fracture into nineteen meaningfully different score bands as protected attributes change. A conventional pairwise fairness test records both as violations. One counterexample each. Very tidy. Also not especially useful. ...