A model-agnostic online certificate-driven calibration framework keeps convolutional, attention-based, and LLM forecasters more stable and accurate under covariate and concept shift
The work proposes a model-agnostic online martingale PAC-Bayesian framework that replaces independent-sample concentration with martingale concentration to yield finite-sample certificates under temporal dependence and distribution shift, and uses the certificate as a surrogate regularizer for online calibration by training a gated residual Bayesian head on top of a fixed forecasting backbone under a predict-then-update protocol, improving stability and accuracy under covariate and concept shift across convolutional, attention-based, and large language model-based forecasters.