Joint upper-bound coverage and route-choice utility: an empirical evaluation on two urban proxy tasks
Quick Answer
This study evaluates the impact of joint upper-bound coverage on route choices using traffic data from Beijing and Chengdu.
Quick Take
Results show that while joint coverage improved significantly, it did not correlate with reduced lateness or travel time, indicating that higher coverage does not guarantee better route utility.
Key Points
- Joint coverage increased from 83.19% to 92.26% in Beijing M1.
- Lateness increased by 0.1633 percentage points in Beijing M1 despite improved coverage.
- Chengdu M1 and M2 showed joint coverage rises from 75.14% to 88.33% and 74.01% to 90.64%, respectively.
- A 14.91% reduction in speed mean absolute error was noted in Chengdu's predictor comparison.
- The study concludes that joint coverage does not imply better downstream route utility.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Whether more accurate traffic forecasts or higher uncertainty coverage improve route decisions is unclear. We evaluate this question with a frozen protocol that separates speed error, joint candidate path upper bound coverage, route selection, and realized loss. Using processed road speed data from Beijing and Chengdu, we construct offline proxy tasks with 150 origin destination pairs, three candidate paths, and 14 test days per city. We compare raw 90th percentile path time bounds with jointly calibrated upper bounds under minimum bound route choice. Joint coverage rises from 83.19% to 92.26% in Beijing M1, from 75.14% to 88.33% in Chengdu M1, and from 74.01% to 90.64% in Chengdu M2. Yet C2 increases lateness by 0.1633, 0.7848, and 0.9200 percentage points, respectively, and mean travel time by 0.588, 3.082, and 4.418 seconds. In a separate Chengdu predictor comparison, a 14.91% reduction in speed mean absolute error accompanies a 1.4571 percentage point reduction in lateness under C0. Joint coverage is therefore not a surrogate for downstream route utility in these frozen tasks the offline results do not establish online or causal benefits.
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.06995 [cs.AI] |
| (or arXiv:2610.06995v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.06995 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaobin Li [view email]
[v1]
Sun, 4 Oct 2026 07:48:03 UTC (1,030 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.