Neural Network Representation of Generalized Parton Distributions (NNGPD)
J. Xu, H. Jang, Z. Panjsheeri et al. (2026)
We present a neural-network-based framework for modeling generalized parton distributions, referred to as NNGPD, in which GPDs are represented as flexible functions constrained through physically motivated integral relations. In this approach, experimental and theoretical information is incorporated into the training procedure via loss functions enforcing convolution integrals that define Compton form factors, as well as Mellin moments related to generalized form factors accessible in lattice QCD. read more
Connected and disconnected contributions to nucleon form factors and parton distributions
Z. Panjsheeri, S. Pandey, B. Semp, and S. Liuti (2025)
Using the framework of generalized parton distribution, we provide a unified interpretation of the connected and disconnected contributions from the ab-initio Euclidean path-integral formulation of the hadronic tensor in both the nucleon elastic form factors and the parton distribution functions. We develop a phenomenology to elucidate non-perturbative contributions to deep inelastic structure functions, which can be extended to observables in heavy-ion collisions probing baryon junctions. read more
Updated flexible global parametrization of generalized parton distributions from elastic and deep inelastic inclusive scattering data
Z. Panjsheeri, D. Q. Adams, A. Khawaja, S. Pandey, K. Tezgin, and S. Liuti (2025)
An updated flexible parametrization of the generalized parton distributions in the quark, antiquark and gluon sectors is presented using constraints from high precision electron nucleon deep inelastic scattering data, as well as from the u̅, d̅ quark and gluonic contributions to the nucleon electromagnetic elastic form factors. The latter include recently updated lattice QCD moment calculations. read more
Generalized Parton Distributions from Symbolic Regression
A. Dotson, Z. Panjsheeri, A. R. Singireddy et al. (2025)
How well can we extract physics content from lattice QCD GPD data obtained in a limited range of kinematics? We use symbolic regression (SR) to address this question. SR finds functional forms from the data, rather than just fitting the data to the investigator’s chosen model. We use the PySR package to extract symbolic expressions from the data to study partonic spatial density distributions. Different from neural networks (NNs), which have the primary advantage of great flexibility but are “black boxes” that are nearly uninterpretable on their own, PySR allows for human-interpretable ML output. read more
Likelihood and Correlation Analysis of Compton Form Factors for Deeply Virtual Exclusive Scattering on the Nucleon
D. Q. Adams, J. Bautista, M. Cuic, A. Khawaja, S. Pandey, Z. Panjsheeri, G.-W. Chern, Y. Li, S. Liuti, M. Boer, M. Engelhardt, G. R. Goldstein, H.-W. Lin, and M. D. Sievert (2024)
A likelihood analysis of the observables in deeply virtual exclusive photoproduction off a proton target is presented. Two processes contribute to the reaction: deeply virtual Compton scattering, where the photon is produced at the proton vertex, and the Bether-Heitler process, where the photon is radiated from the electron. We consider the unpolarized process for which the largest amount of data with all the kinematic dependences are available from corresponding datasets with unpolarized beams and unpolarized targets from Jefferson Lab. We provide and use a method which derives a joint likelihood of the Compton form factors, which parametrize the deeply virtual Compton scattering amplitude in QCD, for each observed combination of the kinematic variables defining the reaction. read more