TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models

This work introduces TSFMAudit, a novel method for auditing data contamination in Time Series Foundation Models (TSFMs) during pretraining. It detects when evaluation datasets have been unduly exposed, leading to overly optimistic performance estimates, by observing unusually efficient adaptation during fine-tuning. The study evaluates TSFMAudit on 6 TSFMs and 187 datasets, addressing a previously unstudied challenge in pretraining contamination auditing for TSFMs.