A Platform, Dataset, and Challenge for Uncertainty-Aware Machine Learning

A new challenge has been set up that focuses on measuring the physics properties of elementary particles with imperfect simulators due to differences in modelling systematic errors. Additionally, the challenge has leveraged a large-compute-scale AI platform for sharing datasets, training models, and hosting machine learning competitions. Our challenge has brought together the physics and machine learning communities to advance our understanding and methodologies in handling systematic (epistemic) uncertainties within AI techniques. The challenge is ongoing at the time of submission but will be completed by the end of October 2024. A comparison of the various methods used by participants and the first lessons will be presented at the workshop.