Murmurations: a case study in AI-assisted mathematics

• URL: http://arxiv.org/abs/2603.09680v1
• Date: Tue, 10 Mar 2026 13:47:39 GMT
• Title: Murmurations: a case study in AI-assisted mathematics
• Abstract summary: We report the emergence of a striking new phenomenon in arithmetic, which we call murmurations.<n>Mutterations can be detected and analyzed using standard interpretability tools from machine learning.<n>In this paper, we present an overview of murmurations, contextualizing them within number theory and AI.
• Score: 0.38887448816036313
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Discovering mathematical concepts through a multi-agent system [3.820195410658766]
  We present a new multi-agent model for computational mathematical discovery.<n>Our system, conceived with research in mind, poses its own conjectures and then attempts to prove them.<n>We claim that the optimisation of the right combination of local processes can lead to surprisingly well-aligned notions of mathematical interestingness.
  arXiv  Detail & Related papers  (2026-03-04T19:13:36Z)
• Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations [4.635620949885696]
  We explore the extent to which narrow models trained to solve a fixed mathematical task learn broader mathematical structure that can be extracted by a researcher or other AI system.<n>We describe a suite of tests designed to assess whether the model captures significant group-theoretic notions such as the identity element, commutativity, or subgroups.<n>Our results suggest that in some cases the representations of even small neural networks can be used to distill interesting abstract structure from new mathematical objects.
  arXiv  Detail & Related papers  (2026-01-29T01:18:22Z)
• Statistics of the Random Matrix Spectral Form Factor [0.0]
  We identify the form factor statistics to next leading order in a $D-1$ expansion.<n>Our findings fully agree with numerics.<n>They are presented in a pedagogical way, highlighting new pathways in the study of statistical signatures at next leading order.
  arXiv  Detail & Related papers  (2025-03-27T11:34:12Z)
• Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models [76.6028674686018]
  We introduce thought-tracing, an inference-time reasoning algorithm to trace the mental states of agents.<n>Our algorithm is modeled after the Bayesian theory-of-mind framework.<n>We evaluate thought-tracing on diverse theory-of-mind benchmarks, demonstrating significant performance improvements.
  arXiv  Detail & Related papers  (2025-02-17T15:08:50Z)
• Graph Stochastic Neural Process for Inductive Few-shot Knowledge Graph Completion [63.68647582680998]
  We focus on a task called inductive few-shot knowledge graph completion (I-FKGC) Inspired by the idea of inductive reasoning, we cast I-FKGC as an inductive reasoning problem. We present a neural process-based hypothesis extractor that models the joint distribution of hypothesis, from which we can sample a hypothesis for predictions. In the second module, based on the hypothesis, we propose a graph attention-based predictor to test if the triple in the query set aligns with the extracted hypothesis.
  arXiv  Detail & Related papers  (2024-08-03T13:37:40Z)
• Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning [49.0767291348921]
  Randomized Numerical Linear Algebra (RandNLA) is an area which uses randomness to develop improved algorithms for ubiquitous matrix problems. This article provides a self-contained overview of RandNLA, in light of these developments.
  arXiv  Detail & Related papers  (2024-06-17T02:30:55Z)
• Review and Prospect of Algebraic Research in Equivalent Framework between Statistical Mechanics and Machine Learning Theory [0.0]
  It is well known that algebraic approaches in statistical mechanics such as operator algebra enable us to analyze phase transition phenomena mathematically.<n>This paper is devoted to the memory of Professor Huzihiro Araki who is a pioneering founder of algebraic research in both statistical mechanics and quantum field theory.
  arXiv  Detail & Related papers  (2024-05-31T11:04:13Z)
• Higher-order topological kernels via quantum computation [68.8204255655161]
  Topological data analysis (TDA) has emerged as a powerful tool for extracting meaningful insights from complex data. We propose a quantum approach to defining Betti kernels, which is based on constructing Betti curves with increasing order.
  arXiv  Detail & Related papers  (2023-07-14T14:48:52Z)
• A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis [128.0532113800092]
  We present a mechanistic interpretation of Transformer-based LMs on arithmetic questions. This provides insights into how information related to arithmetic is processed by LMs.
  arXiv  Detail & Related papers  (2023-05-24T11:43:47Z)
• A Survey of Deep Learning for Mathematical Reasoning [71.88150173381153]
  We review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. Recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning.
  arXiv  Detail & Related papers  (2022-12-20T18:46:16Z)
• Machine-Learning Mathematical Structures [0.0]
  We present a comparative study of the accuracies on different problems. The paradigm should be useful for conjecture formulation, finding more efficient methods of computation, as well as probing into certain hierarchy of structures in mathematics.
  arXiv  Detail & Related papers  (2021-01-15T22:48:19Z)
• Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning [95.18337034090648]
  We propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG) These visual arithmetic problems are in the form of geometric figures. We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task.
  arXiv  Detail & Related papers  (2020-04-25T17:14:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.