Outcome Is Not Verification: Auditing Hidden-State Verifiers with Counterfactual Local Validity

Hidden states can support strong outcome readout without thereby supporting reliable process verification. We make that distinction operational with an audit centered on counterfactual local validity: whether the same step remains valid when the underlying world changes. We instantiate the audit in two structured reasoning domains—arithmetic DAG execution and grounded Horn-style logic—using paired worlds, stored gold/recoverable/doomed traces, and strict same-step flips that hold the current-step text fixed. To isolate the target variable rather than the architecture, we keep the hidden-state extractor family and scorer class fixed and compare only supervision targets: final trace outcome, prefix outcome, local validity, and a flip-rank variant. Across domains, hidden states provide meaningful trace-level outcome readout, but outcome-supervised step scoring does not behave like process verification. Under the same canonical step pools, LocalValidity improves the strongest audit axes, especially strict same-step FlipAcc and PVS. The gains are not uniform across all tests: repaired arithmetic scale remains mixed on first-invalid-step localization, particularly on held-out renderer C, while logic scale remains strongly favorable to LocalValidity even on the same harder transfer slice. The resulting picture is not that local-validity supervision “wins everything,” but that counterfactual local validity exposes a real outcome/process gap while showing that process-verification evidence is metric-dependent and transfer-sensitive even in structured reasoning.