Does Architecture Preference Transfer in Time-Series Forecasting?

Forecasting benchmarks are often reused to infer which architectures should work well on related tasks, but global architecture strength need not imply transferable task-specific preference. We isolate architecture preference as the residual interaction in log forecasting risk after removing architecture-wide strength and task difficulty. Across ten architectures and 41 tasks from eleven datasets, preference is strongly local to dataset identity: residual profiles correlate at $0.800$ across horizons of the same dataset but at $-0.014$ across datasets. When an entire horizon is held out from a previously observed dataset, nearest-horizon reuse recovers $90.8\%$ of held-out pairwise preferences, compared with $43.4\%$ for exchangeable matrix factorization. Matched random-group controls show that this gain is specific to real dataset membership rather than generic grouped parameter sharing. The locality pattern reproduces on a separately executed panel of ten datasets and six fixed architectures (within/across $0.722/0.037$; slope $-0.306$) and is stable across the tested update budgets. Strict leave-one-dataset-out prediction is substantially weaker, showing that observable metadata captures only part of preference on unseen datasets. A frozen-mask evaluation-budget audit further shows that the operational value of local reuse is budget-dependent. Overall, global architecture strength transfers broadly, whereas residual preference is predominantly dataset-local and most reusable across related configurations within an observed dataset.