SOURCE-LINKED INTELLIGENCE

Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

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 effect that isolates a step's own contribution, add the natural direct effect under a pinned downstream, and check the estimators against hand derivations. Both estimands then fail, in the same direction. U

Read original source ↗ Open in workspace

recordType

paper

region

Global