analiza aiqbench
This study critically examines the gap between improved traffic forecasting accuracy and actual signal control performance, revealing that predictive gains often fail to translate into operational benefits due to constraints in action identifiability and temporal observability. By diagnosing specific failure modes such as decision-time leakage and limited effective actions at intersections, the research provides a rigorous framework for evaluating when future information genuinely adds value versus when it merely introduces noise or increased queue times. The findings underscore that deploying advanced AI models in traffic management requires more than just better predictions; it demands a holistic assessment of system dynamics and control constraints to ensure real-world efficacy.
When better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value
arXiv:2610.06992v1 Announce Type: new Abstract: Improved traffic forecasts do not necessarily yield better signal-control decisions. We investigate this gap through a layered diagnostic study using 29 days of reconstructed demand from Xuancheng, China, with seven dates reserved for testing. The framework evaluates point forecasts, conformal intervals, dependence-aware scenarios, and matched closed-loop controllers. Entry-level and movement-level forecasts reduce mean absolute error by 4.03% and 3.92%, respectively, relative to historical means. A nominal 90% conformal interval achieves 90.72% marginal coverage but only 75.66% on an ex-post high-demand subset. Interface audits identify decision-time leakage and reveal that only two of nine controlled intersections offer multiple effective actions. We correct the temporal interface and compare causal forecasts with a five-second event oracle using exhaustive joint-action search. A synthetic positive control demonstrates that future information can reduce the internal rollout cost by 61.5%. On the frozen test dates, however, causal forecasts and the event oracle increase queue vehicle?seconds by 6.09% and 3.39% relative to the matched no-future rollout, while the oracle reduces spillback exposure by 3.78%; paired-day bootstrap intervals cross zero. These findings indicate that forecast value depends on temporal observability, action identifiability, dynamics consistency, and objective alignment. The proposed protocol provides a practical way to diagnose where predictive improvements fail to translate into operational benefits.
Abstract:Improved traffic forecasts do not necessarily yield better signal-control decisions. We investigate this gap through a layered diagnostic study using 29 days of reconstructed demand from Xuancheng, China, with seven dates reserved for testing. The framework evaluates point forecasts, conformal intervals, dependence-aware scenarios, and matched closed-loop controllers. Entry-level and movement-level forecasts reduce mean absolute error by 4.03% and 3.92%, respectively, relative to historical means. A nominal 90% conformal interval achieves 90.72% marginal coverage but only 75.66% on an ex-post high-demand subset. Interface audits identify decision-time leakage and reveal that only two of nine controlled intersections offer multiple effective actions. We correct the temporal interface and compare causal forecasts with a five-second event oracle using exhaustive joint-action search. A synthetic positive control demonstrates that future information can reduce the internal rollout cost by 61.5%. On the frozen test dates, however, causal forecasts and the event oracle increase queue vehicle?seconds by 6.09% and 3.39% relative to the matched no-future rollout, while the oracle reduces spillback exposure by 3.78%; paired-day bootstrap intervals cross zero. These findings indicate that forecast value depends on temporal observability, action identifiability, dynamics consistency, and objective alignment. The proposed protocol provides a practical way to diagnose where predictive improvements fail to translate into operational benefits.
Artificial Intelligence (cs.AI)
arXiv:2610.06992 [cs.AI]
(or arXiv:2610.06992v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.06992 Focus to learn more arXiv-issued DOI via DataCite
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.
Text integral sub licența deschisă a publicației · 298 cuvinte
Subiecte conexe
Post-Quantum Cryptography Explained, the Complete Plain English Guide
Quantum Zeitgeist · 30 aug. 2026
Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCore
AWS · 16 oct. 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · 2 oct. 2026
Echoverse: Deep, evolving environments for computer-use agents
Microsoft Research · 30 iul. 2026