DeCaF combines counterfactual generators and causal models to identify minimal input signal changes that fix CPS failures and derives interpretable assertions that generalize the recovery conditions.
Explaining machine learning classifiers through diverse counterfactual explanations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.
citing papers explorer
-
Towards Counterfactual Explanation and Assertion Inference for CPS Debugging
DeCaF combines counterfactual generators and causal models to identify minimal input signal changes that fix CPS failures and derives interpretable assertions that generalize the recovery conditions.
-
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.