Transfer-Valid Weather-Station Forecasting: Separating Held-Out Computability from Spatial Communication

Fixed-station accuracy does not establish transfer to stations excluded from training. We formalize transfer validity for location-known, observation-held-out forecasting as a property of learned prediction under two distinct boundaries. The parameter boundary excludes dependence on identity-indexed trainable state left untrained by the spatial split. Required trainable quantities are instead shared across stations or generated from permitted inputs. The information boundary restricts prediction and routing to data permitted by the split and available at or before the forecast origin. It allows dynamic routes built from the recent history supplied at inference. WeatherScaleNet instantiates these conditions with shared station functions and static-geographic routing. Its completed computational-position graph has diameter at most two when both interaction axes are present, and balanced layouts give spatial attention cost $\mathcal{O}({\tilde{N}}^{3/2}d)$. Five-seed experiments on global weather stations and physical rain gauges evaluate fixed-station accuracy and random-station and contiguous-region holdout. Fixed-station branch controls favor retaining both interaction axes. Coordinate and elevation representations change rank across settings, feature concatenation can outperform scalar aggregation, and partition granularity has limited influence over the tested range. These findings distinguish learned held-out computation, permitted information use, communication structure, and predictive effectiveness without tying transfer validity to one encoder or routing mechanism.