Outcome-fair credit models often exhibit hidden procedural bias through inconsistent reasoning across groups, which the CEC framework mitigates by enforcing consistent feature attributions via counterfactuals.
Advances in Neural Information Processing Systems , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Data equity, prediction equity, and decision equity are distinct statistical requirements that need separate evaluations to address how racial biases in pulse oximetry measurements lead to treatment disparities.
An algorithm learns a Mahalanobis metric from triplet queries via spectral initialization and gradient descent in the Bradley-Terry model, with convergence guarantees and transfer of individual fairness from estimated to true metric.
citing papers explorer
-
Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
Outcome-fair credit models often exhibit hidden procedural bias through inconsistent reasoning across groups, which the CEC framework mitigates by enforcing consistent feature attributions via counterfactuals.
-
Data (in)equities in data science: Dissecting systemic and systematic biases in pulse oximetry
Data equity, prediction equity, and decision equity are distinct statistical requirements that need separate evaluations to address how racial biases in pulse oximetry measurements lead to treatment disparities.
-
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
An algorithm learns a Mahalanobis metric from triplet queries via spectral initialization and gradient descent in the Bradley-Terry model, with convergence guarantees and transfer of individual fairness from estimated to true metric.