AI RESEARCH
xaitimesynth: A Python Package for Evaluating Attribution Methods for Time Series with Synthetic Ground Truth
arXiv CS.LG
•
ArXi:2603.06781v1 Announce Type: new Evaluating time series attribution methods is difficult because real-world datasets rarely provide ground truth for which time points drive a prediction. A common workaround is to generate synthetic data where class-discriminating features are placed at known locations, but each study currently reimplements this from scratch. We