SciPost Submission Page
Machine learning in top quark physics at ATLAS and CMS
by Matthias Komm
Submission summary
| Authors (as registered SciPost users): | Matthias Komm |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2503.04289v1 (pdf) |
| Date submitted: | March 7, 2025, 9:44 a.m. |
| Submitted by: | Komm, Matthias |
| Submitted to: | SciPost Physics Proceedings |
| Proceedings issue: | The 17th International Workshop on Top Quark Physics (TOP2024) |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Experimental |
Abstract
This note presents an overview of machine-learning-based techniques used in the study of the top quark. The research community has developed a diverse set of ideas and tools, including algorithms for the efficient reconstruction of recorded collision events and innovative methods for statistical inference. Recent applications by the ATLAS and CMS collaborations are also highlighted.
Current status:
Reports on this Submission
Report #1 by Samuel Calvet (Referee 1) on 2025-5-5 (Invited Report)
Strengths
1- The proceedings is clearly written and the presentation of ideas is easy to follow, making the review accessible to a broad audience.
2- The paper provides a well-structured and comprehensive overview of ML-based techniques that are or could be used for top physics
Weaknesses
1- The title and the abstract presents the proceedings as a review of ML techniques used in top physics. Actually only a small fraction of these techniques are used in this field. The rest of these technique are not (yet) used.
2- In section 5, the improvement brought by the ML is not clear. What is the difference with regular reweighting techniques, for example base on matrix element of kinematic ?
Report
The document meets the most of requirements for a publication in SciPost Physics Proceedings.
I would encourage the authors to address the 2 identified weakness.
Requested changes
1- Some sentences should be rephrased to clarify that certain techniques discussed—though not currently standard in top quark physics—could offer valuable contributions to the field if appropriately adapted and adopted.
2- Section5 should more explicitly articulate the advantages introduced by the machine learning approach, particularly in contrast to classical methods, to better highlight the added value of the proposed strategy.
3- page 2, 1srt paragraph: "illustrating superior" would be more precise than "demonstrating superior"
4- Figure 1: caption could be clearer if you specify that is for semi-leptonic ttbar events
Recommendation
Ask for minor revision