# HepLean: Digitalising high energy physics

arXiv: https://arxiv.org/abs/2405.08863 · HTML: https://mlsanity.com/paper/2405.08863/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2024.

## Built on by (most cited first, 10 of 10)

- [miniCTX: Neural Theorem Proving with (Long-)Contexts](https://mlsanity.com/paper/2408.03350/) (2024)
- [A Minimal Agent for Automated Theorem Proving](https://mlsanity.com/paper/2602.24273/) (2026)
- [Lean4Physics: Comprehensive Reasoning Framework for College-level Physics in Lean4](https://mlsanity.com/paper/2510.26094/) (2025)
- [Formalized Hopfield Networks and Boltzmann Machines](https://mlsanity.com/paper/2512.07766/) (2025)
- [Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization](https://mlsanity.com/paper/2604.16347/) (2026)
- [AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics](https://mlsanity.com/paper/2609.05157/) (2026)
- [A Community-driven vision for a new Knowledge Resource for AI](https://mlsanity.com/paper/2506.16596/) (2025)
- [ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization](https://mlsanity.com/paper/2605.22885/) (2026)
- [DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory](https://mlsanity.com/paper/2607.23614/) (2026)
- [Towards Certificate-Driven Software Porting: A Self-Improving Agentic Harness for Scientific Program Optimization](https://mlsanity.com/paper/2609.34069/) (2026)

## Abstract (arXiv)

We introduce HepLean, an open-source project to digitalise definitions, theorems, proofs, and calculations in high energy physics using the interactive theorem prover Lean 4. HepLean has the potential to benefit the high energy physics community in four ways: making it easier to find existing results, allowing the creation of new results using artificial intelligence and automated methods, allowing easy review of papers for mathematical correctness, and providing new ways to teach high energy physics. We will discuss these in detail. We will also demonstrate the digitalisation of three areas of high energy physics in HepLean: Cabibbo-Kobayashi-Maskawa matrices in flavour physics, local anomaly cancellation, and Higgs physics.