When Verifiers Vote Backwards under Verdict Substitution: Signed Pivotal Value in Correlated Self-Consistency

Abstract:Replacing one ballot can change a majority decision only on queries decided by a single vote; this structural fact requires no independence assumption. We study the sign of that change using a labeled, verdict-style intervention: one correctness signal replaces one correctness-indicator ballot in $k{=}7$ self-consistency panels. This diagnostic intervention is not identical to deployed answer-identity plurality. A primary MATH-500 experiment ($n{=}570$) gives a different-model verifier a $+24.2$pp pivotal gain, whereas a role-reversed configuration gives $-11.2$pp; an exploratory code stress test (14 pivotal rows across 9 tasks) gives $-24.5$pp. An exact signed-gain decomposition accounts for all observed signs through the verifier's state-specific accuracy and the composition of the two one-vote tally states, rather than global accuracy or model provenance. Same-source signals lose accuracy on the pivotal stratum (65$\to$44\% in the primary configuration), while error correlations provide a descriptive error-association diagnostic. Controlled degradation and a $k\in\{3,5,7\}$ subset sensitivity analysis probe the stability of the observed pattern around this accounting. Under the evaluated ties-incorrect answer-identity plurality analysis, the structural zero and strong-verifier benefit persist, but the role-reversed harm attenuates to $-0.9$pp and is not significant. The results therefore establish harmful verdict substitution, not universally harmful deployed plurality, and motivate a testable but unverified hypothesis for negative process-reward-model weights.

Artificial Intelligence (cs.AI)

arXiv:2609.26144 [cs.AI]

(or arXiv:2609.26144v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.26144 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.