SciPost logo

SciPost Submission Page

Exploring unsupervised top tagging using Bayesian inference

by Ezequiel Alvarez, Manuel Szewc, Alejandro Szynkman, Santiago A. Tanco, Tatiana Tarutina

Submission summary

Authors (as Contributors): Santiago Tanco
Submission information
Preprint link: scipost_202301_00014v2
Date accepted: 2023-05-22
Date submitted: 2023-03-14 20:46
Submitted by: Tanco, Santiago
Submitted to: SciPost Physics Core
Ontological classification
Academic field: Physics
  • High-Energy Physics - Phenomenology


Recognizing hadronically decaying top-quark jets in a sample of jets, or even its total fraction in the sample, is an important step in many LHC searches for Standard Model and Beyond Standard Model physics as well. Although there exists outstanding top-tagger algorithms, their construction and their expected performance rely on Montecarlo simulations, which may induce potential biases. For these reasons we develop two simple unsupervised top-tagger algorithms based on performing Bayesian inference on a mixture model. In one of them we use as the observed variable a new geometrically-based observable $\tilde{A}_{3}$, and in the other we consider the more traditional $\tau_{3}/\tau_{2}$ $N$-subjettiness ratio, which yields a better performance. As expected, we find that the unsupervised tagger performance is below existing supervised taggers, reaching expected Area Under Curve AUC $\sim 0.80-0.81$ and accuracies of about 69\% $-$ 75\% in a full range of sample purity. However, these performances are more robust to possible biases in the Montecarlo that their supervised counterparts. Our findings are a step towards exploring and considering simpler and unbiased taggers.

Current status:
Accepted in target Journal

Editorial decision: For Journal SciPost Physics Core: Publish
(status: Editorial decision fixed and (if required) accepted by authors)

List of changes

Following the reports of both reviewers, we have made changes to the manuscript that are explicitly shown in magenta

Reports on this Submission

Anonymous Report 2 on 2023-4-14 (Invited Report)


I am happy with the changes made by authors. This paper should be published.

  • validity: high
  • significance: high
  • originality: high
  • clarity: good
  • formatting: good
  • grammar: good

Report 1 by Tilman Plehn on 2023-3-16 (Invited Report)


Thank you to the authors for going through all my comments and complaints, I think the paper is ready to be published.

  • validity: -
  • significance: -
  • originality: -
  • clarity: -
  • formatting: -
  • grammar: -

Login to report or comment