A CNN framework using response functions from gravitational wave mismatches classifies signals as GR or beyond-GR with 33 times better sensitivity than raw waveforms and detects massive gravity deviations at graviton masses around 10^{-23} eV/c².
Xie et al.,Neural Post-Einsteinian Framework for Efficient Theory-Agnostic Tests of General Relativity with Gravitational Waves,Phys
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
gr-qc 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
Neural post-Einsteinian analysis of GWTC-3 finds no GR violation and sets constraints covering both post-Newtonian and beyond-post-Newtonian deviations in a single theory-agnostic setup.
Bayesian analysis of GW170817 with PPE framework and EM polarization constraints shows mild preference for scalar mode in quadrupole harmonics and improves bounds on non-GR parameters by up to 60%.
citing papers explorer
-
Testing General Relativity Through Gravitational Wave Classification: A Convolutional Neural Network Framework
A CNN framework using response functions from gravitational wave mismatches classifies signals as GR or beyond-GR with 33 times better sensitivity than raw waveforms and detects massive gravity deviations at graviton masses around 10^{-23} eV/c².
-
Neural Post-Einsteinian Test of General Relativity with the Third Gravitational-Wave Transient Catalog
Neural post-Einsteinian analysis of GWTC-3 finds no GR violation and sets constraints covering both post-Newtonian and beyond-post-Newtonian deviations in a single theory-agnostic setup.
-
Tests of scalar polarizations with multi-messenger events
Bayesian analysis of GW170817 with PPE framework and EM polarization constraints shows mild preference for scalar mode in quadrupole harmonics and improves bounds on non-GR parameters by up to 60%.