In this article we propose an extension to the typed natural deduction calculus TNDPQ to model verification of counterfactual fairness in probabilistic classifiers. This is obtained formulating specific structural conditions for causal labels and checking that evaluation is robust under their variation.
A Proof System with Causal Labels (Part II): checking Counterfactual Fairness / L. Ceragioli, G. Primiero - In: OVERLAY 2025 : Artificial Intelligence and Formal Verification, Logic, Automata, and Synthesis 2025 / [a cura di] A. Montanari, A. Orlandini, N. Saccomanno, S. Tonetta. - [s.l] : CEUR-WS, 2025. - pp. 181-187 (( 7. Workshop on Artificial Intelligence and Formal Verification, Logic, Automata, and Synthesis Bologna 2025.
A Proof System with Causal Labels (Part II): checking Counterfactual Fairness
L. Ceragioli
Writing – Original Draft Preparation
;G. Primiero
Writing – Original Draft Preparation
2025
Abstract
In this article we propose an extension to the typed natural deduction calculus TNDPQ to model verification of counterfactual fairness in probabilistic classifiers. This is obtained formulating specific structural conditions for causal labels and checking that evaluation is robust under their variation.
| File | Dimensione | Formato | |
|---|---|---|---|
|
paper20.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Licenza:
Creative commons
Dimensione
1.42 MB
Formato
Adobe PDF
|
1.42 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
