Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand

ArXi:2605.19172v1 Announce Type: cross Forecasting urban delivery demand becomes substantially challenging when newly added service regions lack historical records. Existing spatiotemporal forecasters effectively model spatial dependence once sufficient node histories are available. Still, they remain parametric and therefore struggle to recover short-term operational dynamics in cold-start regions. Geospatial embeddings help identify where a region is and what function it serves, yet they do not directly reveal how a similar region behaves under a comparable temporal context.