Research

Paper

AI LLM March 10, 2026

Murmurations: a case study in AI-assisted mathematics

Authors

Yang-Hui He, Kyu-Hwan Lee, Thomas Oliver, Alexey Pozdnyakov

Abstract

We report the emergence of a striking new phenomenon in arithmetic, which we call murmurations. First observed experimentally through averages over large arithmetic datasets, murmurations can be detected and analyzed using standard interpretability tools from machine learning, including principal component weightings, saliency curves, and convolutional filters. Although discovered computationally, they constitute a genuinely new and intriguing phenomenon in arithmetic that can be formulated and investigated using established tools of number theory. In particular, murmurations encode subtle information about Frobenius traces and naturally belong to the framework of arithmetic statistics. More precisely, murmurations connect to central themes surrounding the conjecture of Birch and Swinnerton-Dyer and perspectives from random matrix theory. In this paper, we present an overview of murmurations, contextualizing them within number theory and AI.

Metadata

arXiv ID: 2603.09680
Provider: ARXIV
Primary Category: math.NT
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09680v1</id>\n    <title>Murmurations: a case study in AI-assisted mathematics</title>\n    <updated>2026-03-10T13:47:39Z</updated>\n    <link href='https://arxiv.org/abs/2603.09680v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09680v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We report the emergence of a striking new phenomenon in arithmetic, which we call murmurations. First observed experimentally through averages over large arithmetic datasets, murmurations can be detected and analyzed using standard interpretability tools from machine learning, including principal component weightings, saliency curves, and convolutional filters. Although discovered computationally, they constitute a genuinely new and intriguing phenomenon in arithmetic that can be formulated and investigated using established tools of number theory. In particular, murmurations encode subtle information about Frobenius traces and naturally belong to the framework of arithmetic statistics. More precisely, murmurations connect to central themes surrounding the conjecture of Birch and Swinnerton-Dyer and perspectives from random matrix theory. In this paper, we present an overview of murmurations, contextualizing them within number theory and AI.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='math.NT'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n    <published>2026-03-10T13:47:39Z</published>\n    <arxiv:comment>12 pages, 15 figures</arxiv:comment>\n    <arxiv:primary_category term='math.NT'/>\n    <author>\n      <name>Yang-Hui He</name>\n    </author>\n    <author>\n      <name>Kyu-Hwan Lee</name>\n    </author>\n    <author>\n      <name>Thomas Oliver</name>\n    </author>\n    <author>\n      <name>Alexey Pozdnyakov</name>\n    </author>\n  </entry>"
}