A contrastive self-supervised convolutional autoencoder detects core-collapse supernova gravitational waves with performance comparable to supervised CNNs, better generalization to unseen waveforms, and ~120 kpc sensitive distance under Einstein Telescope noise.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
HIcosmo is a new JAX-based differentiable framework for background cosmology inference that matches Cobaya results while delivering 8.7x CPU and up to 20x GPU speedups.
Combining GWTC-4 standard sirens with TDCOSMO2025 lensing data under the distance sum rule yields H0 = 83.78 +12.53/-10.23 km/s/Mpc (13.6% precision) in one configuration, consistent with both Planck and SH0ES.
Forecasts that cross-correlating 3G GW dark sirens with CSST photometric galaxies yields 1.04% precision on H0 and 2.04% on Omega_m while also constraining GW clustering bias.
Simulations indicate joint Taiji+LISA analysis of five SLGW events yields H0 95% credible interval uncertainties of 0.11 (source redshift unknown) or 0.042 (source redshift known).
citing papers explorer
-
Contrastive self-supervised convolutional autoencoder for core-collapse supernova gravitational-wave detection
A contrastive self-supervised convolutional autoencoder detects core-collapse supernova gravitational waves with performance comparable to supervised CNNs, better generalization to unseen waveforms, and ~120 kpc sensitive distance under Einstein Telescope noise.