- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Letters

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Isolating Unisolated Upsilons with Anomaly Detection in CMS Open Data

Rikab Gambhir1,2,*, Radha Mastandrea3,4,†, Benjamin Nachman4,5,6,7,‡, and Jesse Thaler1,2,§

  • *Contact author: rikab@mit.edu
  • †Contact author: rmastand@berkeley.edu
  • ‡Contact author: nachman@stanford.edu
  • §Contact author: jthaler@mit.edu
PDF

Phys. Rev. Lett. 135, 021902 – Published 8 July, 2025

DOI: https://doi.org/10.1103/vvv3-5kkl

Abstract

We present the first study of anti-isolated Upsilon decays to two muons (ϒ→μ+μ−) in proton-proton collisions at the Large Hadron Collider. Using a machine learning (ML)-based anomaly detection strategy, we “rediscover” the ϒ in 13 TeV CMS Open Data from 2016, despite overwhelming anti-isolated backgrounds. We elevate the signal significance to 6.4σ using these methods, starting from 1.6σ using the dimuon mass spectrum alone. Moreover, we demonstrate improved sensitivity from using an ML-based estimate of the multifeature likelihood compared to traditional “cut-and-count” methods. This is the first ever detection of anti-isolated Upsilons, which can be useful in the study of heavy-flavor fragmentation in quantum chromodynamics. Our Letter demonstrates that it is possible and practical to find real signals in experimental collider data using ML-based anomaly detection, and we distill a readily accessible benchmark dataset from the CMS Open Data to facilitate future anomaly detection developments.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (52)

  1. Per Ernstrom and Leif Lonnblad, Generating heavy quarkonia in a perturbative QCD cascade, Z. Phys. C 75, 51 (1997).
  2. A. Andronic et al., Heavy-flavour and quarkonium production in the LHC era: From proton–proton to heavy-ion collisions, Eur. Phys. J. C 76, 107 (2016).
  3. Reggie Bain, Lin Dai, Andrew Hornig, Adam K. Leibovich, Yiannis Makris, and Thomas Mehen, Analytic and Monte Carlo studies of jets with heavy mesons and quarkonia, J. High Energy Phys. 06 (2016) 121.
  4. Francesco Giovanni Celiberto and Michael Fucilla, Diffractive semi-hard production of a J/ψ or a ϒ from single-parton fragmentation plus a jet in hybrid factorization, Eur. Phys. J. C 82, 929 (2022).
  5. Roel Aaij et al. (LHCb Collaboration), Study of J/ψ production in jets, Phys. Rev. Lett. 118, 192001 (2017).
  6. Armen Tumasyan et al. (CMS Collaboration), Fragmentation of jets containing a prompt J/ψ meson in PbPb and pp collisions at sNN=5.02  TeV, Phys. Lett. B 825, 136842 (2022).
  7. R. Bain, Y. Makris, T. Mehen, L. Dai, and A. K. Leibovich, NRQCD confronts LHCb data on quarkonium production within jets, Phys. Rev. Lett. 119, 032002 (2017).
  8. Geoffrey T. Bodwin, Eric Braaten, and G. Peter Lepage, Rigorous QCD analysis of inclusive annihilation and production of heavy quarkonium, Phys. Rev. D 51, 1125 (1995); 55, 5853(E) (1997).
  9. Naomi Cooke, Measurements of quarkonia and tetraquark production in jets at LHCb, Ph.D. thesis, Glasgow U., 2023.
  10. CMS Collaboration, DoubleMuon primary dataset in NANOAOD format from RunH of 2016 (/DoubleMuon/Run2016H-UL2016_MiniAODv2_NanoAODv9-v1/NANOAOD). CERN Open Data Portal (2024), 10.7483/OPENDATA. CMS.UZD7.Z50M.
  11. Anna Hallin, Joshua Isaacson, Gregor Kasieczka, Claudius Krause, Benjamin Nachman, Tobias Quadfasel, Matthias Schlaffer, David Shih, and Manuel Sommerhalder, Classifying Anomalies THrough Outer Density Estimation (CATHODE). Phys. Rev. D 106, 055006 (2022).
  12. Gregor Kasieczka et al., The LHC Olympics 2020: A community challenge for anomaly detection in high energy physics, Rep. Prog. Phys. 84, 124201 (2021).
  13. T. Aarrestad et al., The dark machines anomaly score challenge: Benchmark data and model independent event classification for the large hadron collider, SciPost Phys. 12, 043 (2022).
  14. Living review of machine learning in high energy physics, https://iml-wg.github.io/HEPML-LivingReview.
  15. Georges Aad et al. (ATLAS Collaboration), Dijet resonance search with weak supervision using s=13  TeV pp collisions in the ATLAS detector, Phys. Rev. Lett. 125, 131801 (2020).
  16. Georges Aad et al. (ATLAS Collaboration), Anomaly detection search for new resonances decaying into a Higgs boson and a generic new particle X in hadronic final states using s=13  TeV pp collisions with the ATLAS detector, Phys. Rev. D 108, 052009 (2023).
  17. Vladimir Chekhovsky et al. (CMS Collaboration), Model-agnostic search for dijet resonances with anomalous jet substructure in proton-proton collisions at s=13  TeV, Rep. Prog. Phys. 88, 067802 (2025).
  18. Georges Aad et al. (ATLAS Collaboration), Search for new phenomena in two-body invariant mass distributions using unsupervised machine learning for anomaly detection at s=13  TeV with the ATLAS detector, Phys. Rev. Lett. 132, 081801 (2024).
  19. Georges Aad et al. (ATLAS Collaboration), Weakly supervised anomaly detection for resonant new physics in the dijet final state using proton-proton collisions at s=13  TeV with the ATLAS detector, arXiv:2502.09770.
  20. Oliver Knapp, Guenther Dissertori, Olmo Cerri, Thong Q. Nguyen, Jean-Roch Vlimant, and Maurizio Pierini, Adversarially learned anomaly detection on CMS open data: Re-discovering the top quark, Eur. Phys. J. Plus 136, 236 (2021).
  21. S. Navas et al. (Particle Data Group), Review of particle physics, Phys. Rev. D 110, 030001 (2024).
  22. CERN Open Data Portal. https://opendata.cern.ch.
  23. A. M. Sirunyan et al. (CMS Collaboration), Performance of the CMS muon detector and muon reconstruction with proton-proton collisions at s=13  TeV, J. Instrum. 13, P06015 (2018).
  24. Albert M Sirunyan et al. (CMS Collaboration), A search for pair production of new light bosons decaying into muons in proton-proton collisions at 13 TeV, Phys. Lett. B 796, 131 (2019).
  25. Cari Cesarotti, Yotam Soreq, Matthew J. Strassler, Jesse Thaler, and Wei Xue, Searching in CMS open data for dimuon resonances with substantial transverse momentum, Phys. Rev. D 100, 015021 (2019).
  26. Edmund Witkowski, Benjamin Nachman, and Daniel Whiteson, Learning to isolate muons in data, Phys. Rev. D 108, 092008 (2023).
  27. Jack H. Collins, Kiel Howe, and Benjamin Nachman, Anomaly detection for resonant new physics with machine learning, Phys. Rev. Lett. 121, 241803 (2018).
  28. J. H. Collins, Kiel Howe, and Benjamin Nachman, Extending the search for new resonances with machine learning, Phys. Rev. D 99, 014038 (2019).
  29. Esteban G. Tabak and Eric Vanden-Eijnden, Density estimation by dual ascent of the log-likelihood, Commun. Math. Sci. 8, 217 (2010).
  30. Ivan Kobyzev, Simon J. D. Prince, and Marcus A. Brubaker, Normalizing flows: An introduction and review of current methods, IEEE Trans. Pattern Anal. Mach. Intell. 43, 3964 (2021).
  31. George Papamakarios, Eric Nalisnick, Danilo Jimenez Rezende, Shakir Mohamed, and Balaji Lakshminarayanan, Normalizing flows for probabilistic modeling and inference, J. Mach. Learn. Res. 22, 2617 (2021).
  32. Search for prompt production of a GeV scale resonance decaying to a pair of muons in proton-proton collisions at s=13  TeV, Report No. CMS-PAS-EXO-21-005, 2023.
  33. Leo Breiman, Jerome Friedman, Charles J. Stone, and R. A. Olshen, Classification and Regression Trees (Chapman and Hall/CRC, 1984).
  34. Jerome H. Friedman, Greedy function approximation: A gradient boosting machine, Ann. Stat. 29, 1189 (2000), https://www.jstor.org/stable/2699986?origin=JSTOR-pdf.
  35. Thorben Finke, Marie Hein, Gregor Kasieczka, Michael Krämer, Alexander Mück, Parada Prangchaikul, Tobias Quadfasel, David Shih, and Manuel Sommerhalder, Tree-based algorithms for weakly supervised anomaly detection, Phys. Rev. D 109, 034033 (2024).
  36. Marat Freytsis, Maxim Perelstein, and Yik Chuen San, Anomaly detection in the presence of irrelevant features, J. High Energy Phys. 02 (2024) 220.
  37. J. Neyman and E. S. Pearson, On the problem of the most efficient tests of statistical hypotheses, Phil. Trans. R. Soc. A 231, 289 (1933).
  38. Eric M. Metodiev, Benjamin Nachman, and Jesse Thaler, Classification without labels: Learning from mixed samples in high energy physics, J. High Energy Phys. 10 (2017) 174.
  39. Markus Ojala and Gemma C. Garriga, Permutation tests for studying classifier performance, in 2009 Ninth IEEE International Conference on Data Mining (2009), pp. 908–913, 10.1109/ICDM.2009.108.
  40. Glen Cowan, Kyle Cranmer, Eilam Gross, and Ofer Vitells, Asymptotic formulae for likelihood-based tests of new physics, Eur. Phys. J. C 71, 1554 (2011); 73, 2501(E) (2013).
  41. Marat Freytsis, Grigory Ovanesyan, and Jesse Thaler, Dark force detection in low energy e-p collisions, J. High Energy Phys. 01 (2010) 111.
  42. K. Kondo, Dynamical likelihood method for reconstruction of events with missing momentum. 1: Method and Toy models, J. Phys. Soc. Jpn. 57, 4126 (1988).
  43. K. Kondo, Dynamical likelihood method for reconstruction of events with missing momentum. 2: Mass spectra for 2→2 processes, J. Phys. Soc. Jpn. 60, 836 (1991).
  44. G. Bohm and G. Zech, Statistics of weighted Poisson events and its applications, Nucl. Instrum. Methods Phys. Res., Sect. A 748, 1 (2014).
  45. Morris L. Swartz et al., A search for doubly charged Higgs scalars in Z decay, Phys. Rev. Lett. 64, 2877 (1990).
  46. S. Atag and K. O. Ozansoy, Realistic constraints on the doubly charged bilepton couplings from Bhabha scattering with LEP data, Phys. Rev. D 68, 093008 (2003).
  47. https://iaifi.org/
  48. R. Mastandrea, B. Nachman, J. Thaler, and R. Gambhir, DoubleMuon primary dataset from RunH of 2016 | Selected features from validated luminosity runs | Awkward array format, Zenodo (2025), 10.5281/zenodo.14618719.
  49. Associated Code: Isolating Unisolated Upsilons with Anomaly Detection in CMS Open Data, https://github.com/hep-lbdl/dimuonAD/.
  50. Tianqi Chen and Carlos Guestrin, Xgboost: A scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16 (ACM, 2016), pp. 785–794, 10.1145/2939672.2939785.
  51. J. Ansel et al., pytorch2: Faster machine learning through dynamic python bytecode transformation and graph compilation, in 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2 (ASPLOS ’24) (ACM, 2024), 10.1145/3620665.3640366.
  52. https://zenodo.org/records/14618719

Outline

Information

Phys. Rev. Lett. 135, 021902– Published 8 July, 2025
  • Received 28 February 2025
  • Revised 1 May 2025
  • Accepted 3 June 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Funded by SCOAP3.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation