Improved traffic forecasts do not automatically yield better signal‑control decisions. We address this gap with a layered diagnostic study using 29 days of reconstructed demand from Xuancheng, China, reserving seven days 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% relative to historical means.
A nominal 90% conformal interval attains 90.72% marginal coverage, yet only 75.66% on an ex‑post high‑demand subset. Interface audits reveal decision‑time leakage and show 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 cut internal rollout cost by 61.5%.
On the frozen test dates, causal forecasts and the 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 offers a practical way to diagnose where predictive improvements fail to translate into operational benefits. Review