We demonstrate that the PFN-framework allows for the accurate estimation of causal effects under weakened assumptions.

We identify the causal effect in a multi-domain setting with unobserved confounders using proxies, given only measurements of the proxy in the target domain, and provide consistent estimators.

We present a new theoretical perspective for the causal bridge that allows a deeper understanding of the impact of its assumptions on causal estimates while yielding an autoencoder formulation that improves causal effect estimation.