SOURCE-LINKED INTELLIGENCE

Path-specific harm decomposition: A partial identification framework

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

A central goal when designing treatment policies is often to "do no harm", that is, to avoid interventions that improve average outcomes while worsening outcomes for some individuals. A widely used notion for harm is the fraction of negatively affected (FNA), defined as the probability that an intervention decreases an individual's outcome. However, in many applications, treatments operate through mediators, and a single "total" FNA can obscure whether harm arises primarily through direct pathways or indirect (mediator-induced) pathways. In this work, we introduce a path-specific analogue of t

Read original source ↗ Open in workspace

recordType

paper

region

Global