Learning to Trace Seiberg Dualities

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Jonathan J. Heckman, Shani Meynet, Alessandro Mininno, Gary Shiu
• Venue: arXiv: hep-th
• Published: 2026-07-30
• Collected: 2026-07-31
• URL: http://arxiv.org/abs/2607.28628v1
• PDF: https://arxiv.org/pdf/2607.28628v1
• DOI: UNKNOWN

Plain-Language Brief

In this paper, the authors use machine learning methods to develop a practical tool for establishing Seiberg dualities in supersymmetric quiver gauge theories. They find that network architectures consisting of transformers and multi-layer perceptrons perform better than deterministic algorithms for quivers with a modest number of nodes (around 10).

What the Document Says

• Dualities are important in physical systems.
• It can be computationally challenging to establish duality between two systems even when rules are known.
• The paper uses machine learning to address this challenge for Seiberg dualities of supersymmetric quiver gauge theories.
• This involves establishing mutations of quivers, similar to 'learning to unknot'.
• Different network architectures consisting of transformers and multi-layer perceptrons tend to outperform deterministic algorithms for quivers with around 10 nodes.
• Adding pathfinder algorithms improves the efficiency and accuracy of the search strategy.

Key Concepts Mentioned

• dualities
• machine learning
• Seiberg dualities
• supersymmetric quiver gauge theories
• mutations of quivers
• transformers
• multi-layer perceptrons
• deterministic algorithms
• pathfinder algorithms

Claims Made by the Document

• Machine learning can be used to efficiently establish Seiberg dualities.
• Transformer and multi-layer perceptron networks perform better than deterministic algorithms for certain quiver configurations.

Evidence Used

• The authors' use of machine learning methods in this paper.
• Results showing the performance of different network architectures.

Methods / Approach

• Machine learning
• Establishing mutations of quivers

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The study is limited to Seiberg dualities of supersymmetric quiver gauge theories. The performance may vary for other types of dualities or physical systems.

Open Questions

• How can the findings be applied to other types of dualities or physical systems?
• What are the implications of this study for the broader field of theoretical physics?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper does not discuss potential applications outside of Seiberg dualities of supersymmetric quiver gauge theories. The authors anticipate that this class of questions can serve as a useful benchmark for frontier AI models applied to theoretical physics, suggesting potential future research directions.

Raw Abstract / Excerpt

Dualities play an important role in establishing both microscopic and emergent phenomena in a wide range of physical systems. In practice, though, it can often be computationally challenging to establish when two systems are dual, even when all of the 'rules of the game' are well-known. Said differently, when confronted with two systems, how can one efficiently establish that they are in fact dual? In this paper we use machine learning methods to address this question for Seiberg dualities of supersymmetric quiver gauge theories. Mathematically, this involves establishing mutations of quivers, which is in turn a variation on the theme of 'learning to unknot'. On the one hand, this leads us to a practical tool for establishing the computational complexity of different dualities. On the other hand, it also allows us to study how different network architectures learn how to trace Seiberg dualities. We find that for quivers with a modest number of quiver nodes (of order $10$), different network architectures consisting of transformers and multi-layer perceptrons tend to outperform deterministic algorithms. Supplementing the network by well-established pathfinder algorithms (essentially 'Google Maps for quivers') leads to an additional improvement in the efficiency and accuracy of the search strategy. We anticipate that this class of questions can serve as a useful benchmark for frontier AI models applied to theoretical physics.