Much of the research in causality in the past 20 years has focused on statistical modeling of systems: i.e., understanding cause and effect on entire populations of entities where large datasets can be employed to learn causal relations. This work has made great progress and has been essential in enabling programs to reason about cause and effect in scenarios which would otherwise be hard for humans due to their complexity or due to uncertainty that exists over large populations. However, another important use for causal reasoning exists and has been understudied in AI, namely, reasoning about cause-and-effect in single streams of events, or “token-level” causality.