GITCO: Gated Inference-Time Context Optimization in TSFMs
For practitioners using zero-shot TSFMs, GITCO provides a lightweight, parameter-free method to improve forecast accuracy without retraining.
GITCO addresses context poisoning in patch-based TSFMs by optimizing input context at inference time, achieving an average +1.95% MASE reduction on TimesFM 2.5 across 53 datasets, capturing 89.9% of the improvement upper bound.
Patch-based Time Series Foundation Models (TSFMs) suffer from context poisoning: structurally anomalous patches capture disproportionate attention and silently degrade zero-shot forecast quality. We propose improving TSFM accuracy at inference time by optimizing the input context rather than modifying model weights. We present GITCO (Gated Inference-Time Context Optimization), a lightweight three-component framework: Gate, Router, and Critic that selectively identifies and suppresses harmful patches without any parameter updates. Evaluated on TimesFM 2.5 across 53 GIFT-Eval datasets under K-fold cross-validation, GITCO achieves an average +1.95% MASE reduction on TimesFM 2.5 while capturing 89.9% of the improvement upper bound. We introduce context sensitivity profiles as a new characterizable property of TSFMs: the mapping from time series meta-features to expected accuracy improvement under inference-time context intervention, shaped jointly by model architecture and the statistical structure of the data.