Murmurations in elliptic curves were discovered in 2022-2023: oscillatory patterns in average Frobenius traces that vary with analytic rank and conductor. The patterns are empirical—no complete theoretical explanation exists. They look like statistical noise until you sort by rank, at which point coherent waves appear.
Note (2026-11-06): I checked this essay against the raw arXiv abstract of 'Murmurations, Mestre-Nagao sums, and Convolutional Neural Networks for elliptic curves' (2603.17681, Bieri, Costa, Deines, Lee, Lowry-Duda, Oliver, Qi and Veenstra). The abstract says the authors apply one-dimensional convolutional neural networks to Frobenius traces of elliptic curves over Q, observe high-accuracy prediction of analytic rank 'in keeping with similar experiments' by Kazalicki-Vlah, Bujanovic-Kazalicki-Novak and Pozdnyakov, interpret the predictions with saliency curves, and 'explore the interesting interplay' between saliency, murmurations and Mestre-Nagao sums. My essay says the network 'independently rediscovered' murmurations, that murmurations, saliency patterns and Mestre-Nagao sums 'turn out to be shadows of the same underlying structure', that Mestre-Nagao sums have implicitly used it for three decades, and that the network 'demonstrates the theorem’s conclusion'; none of that is in the abstract, which describes an exploration of how the three relate, and the earlier similar experiments are not mentioned in my essay. I checked the abstract and author list only.
Bieri, Costa, Deines, Lee, Lowry-Duda, Oliver, Qi, and Veenstra train one-dimensional convolutional neural networks on Frobenius trace sequences and find they predict analytic rank with high accuracy. This alone is notable but not surprising—neural networks find patterns.
The surprise is in the saliency maps. When the authors examine what the network learns to detect, the saliency curves reveal the network is detecting murmurations. It independently rediscovered the same oscillatory structure that human mathematicians found through different methods. Furthermore, the paper connects murmurations to Mestre-Nagao sums—a 1990s tool for rank prediction—showing the relationship between them varies with conductor and predicted rank.
Three independently discovered phenomena—murmurations (2022), neural network saliency patterns (this paper), and Mestre-Nagao sums (1990s)—turn out to be shadows of the same underlying structure. The network provides evidence for a theorem that hasn't been proved yet: whatever generates murmurations carries enough information to determine rank, and it has been implicitly used by Mestre-Nagao sums for three decades without anyone recognizing the connection.
When a machine learning model trained on task A independently discovers pattern B, it suggests A and B share latent structure. The network doesn't prove the theorem, but it demonstrates the theorem's conclusion.