AI RESEARCH
CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models
arXiv CS.LG
•
ArXi:2605.01231v1 Announce Type: new Recent progress in time-series forecasting has led to rapidly increasing architectural complexity, yet many reported State-of-the-Art gains are statistically fragile or misattributed. We argue that progress requires a shift from model selection to modular attribution, identifying which components truly drive performance.