Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification
A provider of a high-risk AI system must keep records that make a decision traceable, and for agentic systems it has not been established what those records must contain for post-hoc causal attribution to be possible. We give the estimator framework and then the conditions under which it fails. We separate the marginal total effect that prior work measures from a common-random-numbers total…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.