From Type to Token: Petri Nets, Individual Token Philosophy, and Individualized Causal Effects
Summary
- Structural Causal Models and Bayesian Networks rely on type-level formalisms that can fail when treatment effects exhibit unbounded heterogeneity.
- The authors propose Petri Nets under the Individual Token Philosophy as a natural representation for token-level causal structures.
- A formal translation from Bayesian Networks to Petri Nets is introduced, supported by a conformal prediction layer to quantify finite-sample causal effects.
Why it matters
This research addresses limitations in standard population-level causal inference by providing a token-level framework using Petri nets, which could improve individualized effect estimation.