SDGFT-ML: Machine-Learning Surrogate and Inverter for Six-Dimensional Geometric Field Theory

Zenodo (CERN European Organization for Nuclear Research) 2026 Open access

Read full text
Authors: David Besemer
DOI: 10.5281/zenodo.18854970
Cited by: 0

Abstract

Machine-learning pipeline for Six-Dimensional Geometric Field Theory (SDGFT). GATv2 surrogate GNN, conditional VAE inverter, ensemble uncertainty, active learning, anomaly detection, and experimental validation against Planck 2018, PDG 2024, NuFIT 5.3, SPARC, DESI, and KiDS. R² = 0.9995 round-trip, χ²/ndof = 1.48, 22 observables, 0 free parameters.

Fields of Study & Subjects

Cosmology and Gravitation Theories Neutrino Physics Research Model Reduction and Neural Networks

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
4 March 2026
Language
EN