REVIEW 10 cited by
Learning Size and Shape of Calabi-Yau Spaces
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present a new machine learning library for computing metrics of string compactification spaces. We benchmark the performance on Monte-Carlo sampled integrals against previous numerical approximations and find that our neural networks are more sample- and computation-efficient. We are the first to provide the possibility to compute these metrics for arbitrary, user-specified shape and size parameters of the compact space and observe a linear relation between optimization of the partial differential equation we are training against and vanishing Ricci curvature.
Forward citations
Cited by 10 Pith papers
-
Warped Numerical Calabi-Yau Metrics
First numerical GKP warped Type IIB flux background on a Dwork quintic, giving a 0.5% throat-volume estimate near the conifold and new metric/harmonic-form/warp-factor techniques.
-
Minimal surfaces, Knots, and Neural Networks
PINNs approximate near-minimal surfaces bounding knots in S^3; their self-intersection numbers align with Fine's conjecture predictions derived from the HOMFLY polynomial.
-
GlobalCY I: A JAX Framework for Globally Defined and Symmetry-Aware Neural K\"ahler Potentials
Global invariant neural models for Kähler potentials outperform local baselines on geometric diagnostics for hard Calabi-Yau hypersurfaces.
-
Balanced Metrics Know About SYZ
Ambient balanced metric coefficients on Calabi-Yau manifolds decay as |ψ|^{-f(α)} near the large complex structure limit, and the exponent function's Legendre transform gives the dual tropical potential expected from SYZ.
-
Black Hole Black Boxes: Numerical Black Hole Metrics via AInstein Neural Networks
Unsupervised Lorentzian PINNs with embedded S^{2} topology recover maximally extended Schwarzschild and yield candidate Petrov type-I vacuum black-hole metrics with genuinely trapped interiors.
-
Calabi-Yau Metrics with Full Moduli Dependence
Approximate analytic Ricci-flat metrics on a one-parameter bi-cubic Calabi-Yau family with explicit moduli dependence obtained via symbolic regression on numerical data, achieving percent-level agreement.
-
Lost in Translation: Moduli Stabilization from EFT to Eleven Dimensions
Explicit 11D solutions show flux stabilization of T^4/Z2 moduli in EFT does not match the full theory, with non-Lorentz-invariant deformations stabilizing a mix of volume and shape moduli instead.
-
Machine Learning Free Quotients of CICYs
Machine-learning classifiers, especially a multi-head attention model, correctly identify almost all free Z2, Z3, Z4, and Z2xZ2 quotients of CICYs on held-out manifolds, with only three missed Z2xZ2 cases.
-
Pre-Strings Lectures on Artificial Intelligence
Lecture notes define neural-network field theory and survey how it recovers known QFT/string results plus applied AI techniques for string problems.
-
Interpretable Analytic Calabi-Yau Metrics via Symbolic Distillation
The Ricci-flat metric's determinant ratio on the Dwork quintic is reproduced to R²=0.9994 by a five-term symbolic formula in two symmetric invariants, with moduli entering only through fitted coefficients.
Discussion (0). Sign in to comment.