When Interpretability Is Unequally Distributed: Fairness in Hybrid Interpretable Models

ArXi:2605.28626v1 Announce Type: new Hybrid interpretable models combine a transparent component with a black-box model by assigning some examples to the former and deferring the rest to the latter. While this design enables flexible tradeoffs between accuracy and interpretability, it also raises a distinct procedural fairness concern: some graphic groups may systematically receive interpretable decisions, while others are disproportionately routed to a black box.