activity
20242026
collaborators

7 papers

cs.AI2026

Personalized Causal Recourse: A Human-In-The-Loop Approach

Denise Tampieri, Giovanni De Toni, Paolo Giudici

Algorithmic recourse addresses the challenge of providing tailored recommendations to users affected by unfavorable machine learning decisions, in potentially high-stakes scenarios…

cs.LG2026

I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models

Barbara Tarantino, Gennaro Auricchio, Paolo Giudici

Deep learning models are increasingly used in scientific prediction tasks where strong benchmark performance is often interpreted as evidence of scientifically meaningful behavior.…

cs.LG2026

ISAAC: Auditing Causal Reasoning in Deep Models for Drug-Target Interaction

Barbara Tarantino, Sun Kim, Yijingxiu Lu +1

Deep learning models for drug--target interaction (DTI) prediction often achieve strong benchmark performance without necessarily relying on mechanistically meaningful molecular fe…

cs.AI2025

AI Harmonics: a human-centric and harms severity-adaptive AI risk assessment framework

Sofia Vei, Paolo Giudici, Pavlos Sermpezis +2

The absolute dominance of Artificial Intelligence (AI) introduces unprecedented societal harms and risks. Existing AI risk assessment models focus on internal compliance, often neg…

q-fin.PM2025

Building crypto portfolios with agentic AI

Antonino Castelli, Paolo Giudici, Alessandro Piergallini

The rapid growth of crypto markets has opened new opportunities for investors, but at the same time exposed them to high volatility. To address the challenge of managing dynamic po…

stat.ML2025

Group Shapley with Robust Significance Testing and Its Application to Bond Recovery Rate Prediction

Jingyi Wang, Ying Chen, Paolo Giudici

We propose Group Shapley, a metric that extends the classical individual-level Shapley value framework to evaluate the importance of feature groups, addressing the structured natur…