RAEGL：面向时间偏移下选择性上下文路由的风险感知证据门控学习
RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift
浏览论文内容
中文总结 AI 辅助
提出RAEGL框架，通过风险感知证据门控在时间偏移下选择性激活上下文修正，默认保留全局预测器，实验证明可避免有害部署并显式化机会成本。
中文摘要 AI 辅助
上下文特化可以提高预测准确性，但在时间分布偏移下，基于某一历史区间选择的修正可能变得不可靠。为解决这一问题，我们提出RAEGL，一种用于选择性上下文预测的风险感知证据门控学习框架。RAEGL默认保留经过验证的全局预测器，仅当部署前证据支持使用上下文残差时才激活它。该框架将候选选择与门控校准分离，并联合评估随机化显著性、实际有意义的增益和时间稳定性。在真实世界审计和受控面板上的实验表明，RAEGL可以防止有害的上下文部署，同时使保守的机会成本明确化。在重建的Our World in Data审计中，精确回退避免了由两个验证选择的修正导致的RMSE退化0.0960和0.0239。在密封的World Development Indicators评估中，一个基于区域的修正通过了随机化检验，但因增益仅为0.000092、其国家聚类的95%置信区间跨越零、且仅0.02%的bootstrap复制达到实际阈值而被保留。在受控面板中，稳定性和支持感知扩展在97.2%的强稳定上下文运行中激活，同时拒绝所有高漂移设置。这些结果支持RAEGL作为一种可审计的、基于证据的机制，用于管理上下文部署风险，并作为验证驱动上下文选择的保守替代方案。
英文摘要
Contextual specialization can improve forecasting accuracy, but a correction selected on one historical interval may become unreliable under temporal distribution shift. To address this issue, we propose RAEGL, a Risk-Aware Evidence-Gated Learning framework for selective contextual forecasting. RAEGL retains a validated global predictor by default and activates a contextual residual only when pre-deployment evidence supports its use. The framework separates candidate selection from gate calibration and jointly evaluates randomization significance, practically meaningful gain, and temporal stability. Experiments on real-world audits and controlled panels show how RAEGL can prevent harmful contextual deployment while making conservative opportunity costs explicit. In a reconstructed Our World in Data audit, exact fallback avoids RMSE degradations of 0.0960 and 0.0239 caused by two validation-selected corrections. In a sealed World Development Indicators evaluation, a region-based correction passes the randomization test but is withheld because its gain is only 0.000092, its country-clustered 95% confidence interval crosses zero, and only 0.02% of bootstrap replicates reach the practical threshold. In controlled panels, the stability- and support-aware extension activates in 97.2% of strong, stable-context runs while rejecting all high-drift settings. These results support RAEGL as an auditable, evidence-based mechanism for managing contextual deployment risk and as a conservative alternative to validation-driven contextual selection.
