Goodness-of-fit for amplitude analysis with anomaly detection

Amplitude analysis serves as a pivotal tool in hadron spectroscopy, fundamentally involving a series of likelihood fits to multi-dimensional experimental distributions. While numerous robust goodness-of-fit tests are available for low-dimensional scenarios, evaluating goodness-of-fit in amplitude analysis poses significant challenges. In this work, we introduce a powerful goodness-of-fit test leveraging a machine-learning-based anomaly detection method.