Saved in:
Bibliographic Details
Main Authors: Nareklishvili, Maria, Polson, Nicholas, Sokolov, Vadim
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.17894
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915212871860224
author Nareklishvili, Maria
Polson, Nicholas
Sokolov, Vadim
author_facet Nareklishvili, Maria
Polson, Nicholas
Sokolov, Vadim
contents We present generative artificial intelligence (AI) to empirically validate fundamental laws of physics, focusing on the Stefan-Boltzmann law linking stellar temperature and luminosity. Our approach simulates counterfactual luminosities under hypothetical temperature regimes for each individual star and iteratively refines the temperature-luminosity relationship in a deep learning architecture. We use Gaia DR3 data and find that, on average, temperature's effect on luminosity increases with stellar radius and decreases with absolute magnitude, consistent with theoretical predictions. By framing physics laws as causal problems, our method offers a novel, data-driven approach to refine theoretical understanding and inform evidence-based policy and practice.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17894
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative AI for Validating Physics Laws
Nareklishvili, Maria
Polson, Nicholas
Sokolov, Vadim
Solar and Stellar Astrophysics
Astrophysics of Galaxies
Artificial Intelligence
We present generative artificial intelligence (AI) to empirically validate fundamental laws of physics, focusing on the Stefan-Boltzmann law linking stellar temperature and luminosity. Our approach simulates counterfactual luminosities under hypothetical temperature regimes for each individual star and iteratively refines the temperature-luminosity relationship in a deep learning architecture. We use Gaia DR3 data and find that, on average, temperature's effect on luminosity increases with stellar radius and decreases with absolute magnitude, consistent with theoretical predictions. By framing physics laws as causal problems, our method offers a novel, data-driven approach to refine theoretical understanding and inform evidence-based policy and practice.
title Generative AI for Validating Physics Laws
topic Solar and Stellar Astrophysics
Astrophysics of Galaxies
Artificial Intelligence
url https://arxiv.org/abs/2503.17894