Domain: Causal AI & Interpretability

Expected causal effect of a treatment.

Directed acyclic graph encoding causal relationships.

What would have happened under different conditions.

Models effects of interventions (do(X=x)).

Variable enabling causal inference despite confounding.

Probability of treatment assignment given covariates.

Trend reversal when data is aggregated improperly.

Formal model linking causal mechanisms and variables.