ML Referee

Evaluate up to 1,000 candidate features in one run. ML Referee provides independent evidence for feature selection, bounded model repair, and research prioritization without requiring a separate ablation run per feature. For machine-learning researchers and practitioners working with supervised prediction or forecasting, it checks submitted inputs, runs supported evaluations with user authorization, and retrieves results. Results are evidence within the declared evaluation setup, not guarantees of future performance or deployment readiness. An ML Referee account is required. Access requirements are described on the ML Referee website.