Quantum-inspired deep neural networks extract Compton form factors from JLab data with higher predictive accuracy and tighter uncertainties than classical DNNs on pseudodata benchmarks, then applied to real measurements.
A fitter code for Deep Virtual Compton Scattering and Generalized Parton Distributions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We have developped a fitting code based on the leading-twist handbag Deep Virtual Compton Scattering (DVCS) amplitude in order to extract the Generalized Parton Distributions (GPD) information from DVCS observables in the valence region. In a first stage, with simulations and pseudo-data, we show that the full GPD information can be recovered from experimental data if enough observables are measured. If only part of these observables are measured, valuable information can still be extracted, certain observables being particularly sensitive to certain GPDs. In a second stage, we make a practical application of this code to the recent DVCS Jefferson Lab Hall A data from which we can extract numerical constraints for the two $H$ GPD Compton Form Factors.
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compton Form Factor Extraction using Quantum Deep Neural Networks
Quantum-inspired deep neural networks extract Compton form factors from JLab data with higher predictive accuracy and tighter uncertainties than classical DNNs on pseudodata benchmarks, then applied to real measurements.