5 projects
treecf
Constrained, threshold-aware counterfactual explanations for tree ensembles (XGBoost, LightGBM, CatBoost, sklearn) — fast Rust genetic search, exact optimality proofs, certified infeasibility, and recourse regions.
probcal
Universal post-hoc probability calibration for binary classifiers: methods, metrics, diagnostics, and auditable offsetting — numpy-only.
swift-monitoring
SWIFT: SHAP-Weighted Impact Feature Testing for Model-Aware Distribution Monitoring
flaggam
FlagGAM: rule-basis generalized additive models for explainable tabular prediction (Zhao & Welsch, 2026; from-scratch implementation).
concept-graph-xai
Concept-graph aware visualisation of model feature usage and importance, with concept-level ablation metrics.
