SciPost Submission Page
Modern Machine Learning and Particle Physics Phenomenology at the LHC
by Maria Ubiali
Submission summary
| Authors (as registered SciPost users): | Maria Ubiali |
| Submission information | |
|---|---|
| Preprint Link: | scipost_202510_00040v1 (pdf) |
| Date submitted: | Oct. 22, 2025, 8:32 p.m. |
| Submitted by: | Maria Ubiali |
| Submitted to: | SciPost Physics Proceedings |
| Proceedings issue: | The 2nd European AI for Fundamental Physics Conference (EuCAIFCon2025) |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Phenomenological |
Abstract
Modern machine learning is driving a paradigm shift in particle physics phenomenology at the Large Hadron Collider. This short review examines the transformative role of machine learning across the entire theoretical prediction pipeline, from parton-level calculations to full simulations. We discuss applications to scattering amplitude computations, phase space integration, Parton Distribution Function determination, and parameter extraction. Some critical frontiers for the field including uncertainty quantification, the role of symmetries, and interpretability are highlighted.
Current status:
In voting
Reports on this Submission
Strengths
1.) Concise and complete coverage of the use of Machine Learning in HEP Phenomenology
2.) Clear presentation which can be followed by non-experts
3.) Excellent writing style, language and grammar
2.) Clear presentation which can be followed by non-experts
3.) Excellent writing style, language and grammar
Weaknesses
-
Report
The author does a commendable job summarizing the use of Machine Learning methods across the field of particle physics phenomenology. Despite the topic's broad nature, the work gives a wide and complete overview. For each covered sub-field of ML applications, the challenges faced in the field are first introduced in a way that does not require extensive preexisting knowledge from the reader, and in a way that directly leads into how ML is used to address these challenges. The provided references are extensive and well chosen.
Throughout the paper the grammar and language is excellent, and the writing style is enjoyable to read.
As such, I find this paper fitting for Scipost Proceedings, and would recommend publication as is.
Throughout the paper the grammar and language is excellent, and the writing style is enjoyable to read.
As such, I find this paper fitting for Scipost Proceedings, and would recommend publication as is.
Recommendation
Publish (easily meets expectations and criteria for this Journal; among top 50%)