A symmetry-equivariant generative model trained on thermal snapshots of a 1D O(3) spin glass recovers the microscopic Hamiltonian parameters with 99.7% cosine similarity to ground truth through linear inversion of its learned score field.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.dis-nn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Autonomous Emergence of Hamiltonian in Deep Generative Models
A symmetry-equivariant generative model trained on thermal snapshots of a 1D O(3) spin glass recovers the microscopic Hamiltonian parameters with 99.7% cosine similarity to ground truth through linear inversion of its learned score field.