NeuralCert: certified computational discovery of extremal mathematical constructions
Abstract
Neural networks are becoming popular in solving mathematical problems, but stochastic models do not provide mathematical exactness by themselves. This study introduces a discovery-to-certification framework in which high-dimensional variational trial functions are learned in a compact separable representation, spectrally diagnosed and pruned, and then certified exactly through multimodular evaluation. Exact certification makes the numerical proofs fully explicit and independently verifiable. This framework can be run on a standard personal computer. Across three extremal problems, we show that neural optimization can contribute to rigorous mathematics in three distinct ways: by discovering improved constructions, by exposing empirical invariants that lead to proofs, and by revealing optimization barriers whose geometry motivates new analytic or numerical representations. More broadly, these results suggest a path toward AI-assisted mathematics in which flexible computational discovery and exact certification become complementary components of a single rigorous workflow.
Related
- The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence
- Large-Scale Autonomous Discovery of Kissing Number Constructions
- Towards Learning-Guided Discovery of Extremal Geometric Constructions: A PatternBoost Study
- Why the Kellogg Mesh Is Radial: A Mathematical Explanation of a Classical Computational Benchmark
- KnottedGraph: Scalable knotted-graph topology for scientific and mathematical discovery
BibTeX
@misc{roeling2026neuralcert,
title = {{NeuralCert: certified computational discovery of extremal mathematical constructions}},
author = {Mark Patrick Roeling},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.30296},
eprint = {2609.30296},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.30296},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - NeuralCert: certified computational discovery of extremal mathematical constructions
AU - Mark Patrick Roeling
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.30296
UR - https://arxiv.org/abs/2609.30296
AB - Neural networks are becoming popular in solving mathematical problems, but stochastic models do not provide mathematical exactness by themselves. This study introduces a discovery-to-certification framework in which high-dimensional variational trial functions are learned in a compact separable representation, spectrally diagnosed and pruned, and then certified exactly through multimodular evaluation. Exact certification makes the numerical proofs fully explicit and independently verifiable. This framework can be run on a standard personal computer. Across three extremal problems, we show that neural optimization can contribute to rigorous mathematics in three distinct ways: by discovering improved constructions, by exposing empirical invariants that lead to proofs, and by revealing optimization barriers whose geometry motivates new analytic or numerical representations. More broadly, these results suggest a path toward AI-assisted mathematics in which flexible computational discovery and exact certification become complementary components of a single rigorous workflow.
ER -