You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A full-stack SaaS-grade web app where teams upload a dataset + trained model (or plug in an API endpoint) and receive a comprehensive, interactive fairness audit report. Built to be genuinely enterprise-usable, not a toy.
Four-stage fairness audit for production ML, run across eight evaluations and seven public data sources. Baseline disparity predicts whether a post-processing constraint helps: demographic parity improved in 9 of 14 high-disparity pairs and worsened in 3 of 4 near-fair ones. JASIST submission, September 2026
A-ICF: Auditing, Not Predicting — A Causal Bias-Decomposition Framework for Clinical Fairness. Code, Figures, and Tables for OMLET 2026 (Paper ID: 596).