Routeaudit improves multi-verifier routing with adaptive interaction analysis
ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing
Artificial IntelligenceComputation and LanguageMachine Learning
Summary
Many systems check data quality using multiple verifiers, but it’s hard to fairly compare different ways of routing checks because the set of verifiers and other factors can change. The authors introduce ROUTEAUDIT, a method that treats verifier routing as a contract with measurable parts to fairly compare different routing policies. Their approach quantifies the differences in routing policies and provides tight error bounds, helping identify which routing strategy actually improves quality. They tested it on real data caches and task requests, showing it can accurately measure improvement and provide error guarantees.
What this means in practice
- •For data validation teams: Evaluate and compare multi-verifier routing policies with guaranteed quality attribution under changing verifier sets and resources.
- •For quality assurance engineers: Use attribution certificates from ROUTEAUDIT to validate adaptive routing decisions and ensure consistent quality improvements in verification workflows.
Authors
Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Tianshu Fu, Daren Zha, Jun Xiao
Abstract
Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information filtration, or scorer changes with the policy. We formulate verifier routing as a contract-conditioned identification problem. The contract records request support, verifier catalog, realized availability, resource accounting, online filtration, and post-trace scoring; a matched route contrast changes only the policy coordinate. ROUTEAUDIT adds three measurable objects to this contract. A contract lattice averages coordinate increments over every admissible bridge order and reports the resulting attribution together with its path sensitivity. A policy-independent response tape identifies paired sequential contrasts when adaptive policies reveal different observations. For incomplete matching, request-level bounds use whichever potential outcome remains observed and give a sharp finite-population interval. The protocol commits paid observations and ledger events before the oracle join and returns an attribution certificate for each comparison. On two held-out raw-tail caches, matched static SF+SA equals the cascade, assigning the apparent gains of 0.1797 and 0.1250 over full static to the verifier-set edge. On 1,319 held-out task requests, the learned and RLVR studies report quality 0.9522 and 0.9553 versus 0.9484 for matched static; the RLVR-static paired difference is +0.0068 with a request-paired interval $[0.0015,0.0122]$ and a training-seed-by-request hierarchical interval $[0.0006,0.0131]$. Controlled attribution recovery yields route mean absolute error 0.0011 and endpoint reconstruction error 0.0004. Factorial, bridge-order, and stochastic-provider studies evaluate the certificate interface; RLVR supplies a learned-policy stress test under the same identification contract.