DeepMET is a neural-network-based missing transverse momentum estimator that improves resolution by 10-30% over existing CMS methods across a range of final states.
Simplified Models for a First Characterization of New Physics at the LHC
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Low-energy SUSY and several other theories that address the hierarchy problem predict pair-production at the LHC of particles with Standard Model quantum numbers that decay to jets, missing energy, and possibly leptons. If an excess of such events is seen in LHC data, a theoretical framework in which to describe it will be essential to constraining the structure of the new physics. We propose a basis of four deliberately simplified models, each specified by only 2-3 masses and 4-5 branching ratios, for use in a first characterization of data. Fits of these simplified models to the data furnish a quantitative presentation of the jet structure, electroweak decays, and heavy-flavor content of the data, independent of detector effects. These fits, together with plots comparing their predictions to distributions in data, can be used as targets for describing the data within any full theoretical model.
fields
hep-ex 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DeepMET: Improving missing transverse momentum estimation with a deep neural network
DeepMET is a neural-network-based missing transverse momentum estimator that improves resolution by 10-30% over existing CMS methods across a range of final states.