Speaker
Description
Reconstructing low-dimensional truth labels from high-dimensional detector data is a central challenge in any experiment that relies on robust mappings across this so-called domain gap, from multi-particle final states in high-energy physics to large-scale early-universe structure in cosmological surveys. We introduce a new method to bridge this domain gap with an intermediate, synthetic representation of truth that differs from methods operating purely in latent space, such as normalizing flows or invertible approaches, in that the synthetic data is specifically engineered to represent intrinsic detector hardware capabilities of the system at hand. By encoding physical properties of the detector response available only in full simulation, such synthetic representations result in a less lossy compression and recovery than a direct mapping from truth to experimental data. We demonstrate this concept with full simulation of a dual-readout crystal electromagnetic calorimeter for future colliders, in which the synthetic data is constructed to be the simulated detector hits corresponding to photon tracks of scintillation and Cerenkov photons. We refer to these signals as simulated observables as they would not be physical observables in a real detector, but are nonetheless representations of a real physical process. We show that the synthetic representation naturally anchors the neural network architecture to a known physical method, in this case the dual-readout correction, opening new avenues for machinistic interpretability and explainability of ML methods in physics.