RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

Qian Sun, Yong-Ming Tian, Jia-Wei Huang, Cheng Feng, Shao-Qun Zhang|July 7, 2026arXiv

Key Takeaway

Real-world multivariate time series data substantially improves foundation model generalization compared to synthetic data, suggesting that practitioners should prioritize real-world datasets when pretraining time series models.

Summary

This paper introduces RMISC, a large-scale collection of 200 real-world multivariate time series datasets with 142 billion data points across diverse domains.

data scaling evaluation

Key Terms

foundation-models zero-shot-generalization multivariate-time-series pretraining out-of-distribution