Machine learning techniques for jet reconstruction at LHCb and application to the search for H→bb¯ and H→cc¯ in s=13 TeV pp collisions

The LHCb collaboration

doi:10.1007/JHEP07(2026)276

Machine learning techniques for jet reconstruction at LHCb and application to the search for H→bb¯ and H→cc¯ in s=13 TeV pp collisions

The LHCb collaboration

National Institute for Subatomic Physics
University of Warwick
University of Zurich
University of Liverpool
Syracuse University
Instituto Galego de Física de Altas Enerxías (IGFAE)
University of Bristol
Uppsala University
Université Paris-Saclay
University of Michigan, Ann Arbor
Université Clermont Auvergne
AGH University of Krakow
National Institute for Nuclear Physics
TU Dortmund University
Vilnius University
CERN
University of Cambridge
Sorbonne Université
Universidade Federal do Rio de Janeiro
Peking University
University of A Coruna
University of Chinese Academy of Sciences
Consejo Nacional de Rectores (CONARE)
CPPM
Swiss Federal Institute of Technology Lausanne
Massachusetts Institute of Technology
Laboratoire Leprince-Ringuet
University of Oxford
Heidelberg University
Ruhr University Bochum
Centro Brasileiro de Pesquisas Físicas
Pontifícia Universidade Católica do Rio de Janeiro
University of Manchester
University of Edinburgh
CAS - Institute of High Energy Physics
Ramon Llull University
Kyiv National Taras Shevchenko University
Henryk Niewodniczanski Institute of Nuclear Physics of the Polish Academy of Sciences
University of Bonn
Imperial College London
Université Savoie Mont Blanc
Los Alamos National Laboratory
Maastricht University
Monash University
Cracow University of Technology
Ohio State University
Wuhan University
University of Barcelona
Tsinghua University
Eötvös Loránd University
NASU - Institute of Nuclear Research
Horia Hulubei National Institute of Physics and Nuclear Engineering
University of Glasgow
University of Cincinnati
Hunan University
University of Groningen
Central China Normal University
University College Dublin
South China Normal University
Rutherford Appleton Laboratory
University of Valencia
University of Maryland, College Park
NASU - Kharkov Institute of Physics and Technology
University of Freiburg
National Centre for Nuclear Research
RWTH Aachen University
Universidad Nacional de Colombia
University of Birmingham
Vrije Universiteit Amsterdam
Henan Normal University
Lanzhou University
Max Planck Institute for Nuclear Physics
Universidad Andrés Bello

Research output: Contribution to journal › Article › peer-review

Abstract

Two machine learning techniques for jet measurements at the LHCb experiment are presented: a regression-based method for jet-energy calibration and a deep neural network algorithm for jet flavour tagging, distinguishing between b-quark, c-quark, and light parton jets. These techniques are applied to a search for inclusive H→bb¯ and H→cc¯ decays using a LHCb dataset corresponding to an integrated luminosity of 1.6 fb⁻¹. The observed (expected) 95% confidence level upper limits correspond to 6.6 (11.1) times the SM cross-section for the H→bb¯ process, and 1003 (1834) times the SM cross-section for the H→cc¯ process.

Original language	English
Article number	276
Journal	Journal of High Energy Physics
Volume	2026
Issue number	7
DOIs	https://doi.org/10.1007/JHEP07(2026)276
State	Published - Jul 2026
Externally published	Yes

Keywords

Hadron-Hadron Scattering
Higgs Physics
Jet Physics
Jets

Access to Document

10.1007/JHEP07(2026)276

Cite this

@article{0da365023a8a4224a3dc623a14da1efa,

title = "Machine learning techniques for jet reconstruction at LHCb and application to the search for H→bb¯ and H→cc¯ in s=13 TeV pp collisions",

abstract = "Two machine learning techniques for jet measurements at the LHCb experiment are presented: a regression-based method for jet-energy calibration and a deep neural network algorithm for jet flavour tagging, distinguishing between b-quark, c-quark, and light parton jets. These techniques are applied to a search for inclusive H→bb¯ and H→cc¯ decays using a LHCb dataset corresponding to an integrated luminosity of 1.6 fb−1. The observed (expected) 95\% confidence level upper limits correspond to 6.6 (11.1) times the SM cross-section for the H→bb¯ process, and 1003 (1834) times the SM cross-section for the H→cc¯ process.",

keywords = "Hadron-Hadron Scattering, Higgs Physics, Jet Physics, Jets",

author = "\{The LHCb collaboration\} and R. Aaij and Abdelmotteleb, \{A. S.W.\} and \{Abellan Beteta\}, C. and F. Abudin{\'e}n and T. Ackernley and Adefisoye, \{A. A.\} and B. Adeva and M. Adinolfi and P. Adlarson and C. Agapopoulou and Aidala, \{C. A.\} and Z. Ajaltouni and S. Akar and K. Akiba and M. Akthar and P. Albicocco and J. Albrecht and R. Aleksiejunas and F. Alessio and \{Alvarez Cartelle\}, P. and R. Amalric and S. Amato and Amey, \{J. L.\} and Y. Amhis and L. An and L. Anderlini and M. Andersson and P. Andreola and M. Andreotti and \{Andres Estrada\}, S. and A. Anelli and D. Ao and C. Arata and F. Archilli and Z. Areg and M. Argenton and \{Arguedas Cuendis\}, S. and L. Arnone and A. Artamonov and M. Artuso and E. Aslanides and \{Ata{\'i}de Da Silva\}, R. and M. Atzeni and B. Audurier and Authier, \{J. A.\} and D. Bacher and \{Bachiller Perea\}, I. and S. Bachmann and M. Bachmayer and \{Calderon Ramirez\}, S.",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2026.",

year = "2026",

month = jul,

doi = "10.1007/JHEP07(2026)276",

language = "Ingl{\'e}s",

volume = "2026",

journal = "Journal of High Energy Physics",

issn = "1029-8479",

number = "7",

}

TY - JOUR

T1 - Machine learning techniques for jet reconstruction at LHCb and application to the search for H→bb¯ and H→cc¯ in s=13 TeV pp collisions

AU - The LHCb collaboration

AU - Aaij, R.

AU - Abdelmotteleb, A. S.W.

AU - Abellan Beteta, C.

AU - Abudinén, F.

AU - Ackernley, T.

AU - Adefisoye, A. A.

AU - Adeva, B.

AU - Adinolfi, M.

AU - Adlarson, P.

AU - Agapopoulou, C.

AU - Aidala, C. A.

AU - Ajaltouni, Z.

AU - Akar, S.

AU - Akiba, K.

AU - Akthar, M.

AU - Albicocco, P.

AU - Albrecht, J.

AU - Aleksiejunas, R.

AU - Alessio, F.

AU - Alvarez Cartelle, P.

AU - Amalric, R.

AU - Amato, S.

AU - Amey, J. L.

AU - Amhis, Y.

AU - An, L.

AU - Anderlini, L.

AU - Andersson, M.

AU - Andreola, P.

AU - Andreotti, M.

AU - Andres Estrada, S.

AU - Anelli, A.

AU - Ao, D.

AU - Arata, C.

AU - Archilli, F.

AU - Areg, Z.

AU - Argenton, M.

AU - Arguedas Cuendis, S.

AU - Arnone, L.

AU - Artamonov, A.

AU - Artuso, M.

AU - Aslanides, E.

AU - Ataíde Da Silva, R.

AU - Atzeni, M.

AU - Audurier, B.

AU - Authier, J. A.

AU - Bacher, D.

AU - Bachiller Perea, I.

AU - Bachmann, S.

AU - Bachmayer, M.

AU - Calderon Ramirez, S.

PY - 2026/7

Y1 - 2026/7

N2 - Two machine learning techniques for jet measurements at the LHCb experiment are presented: a regression-based method for jet-energy calibration and a deep neural network algorithm for jet flavour tagging, distinguishing between b-quark, c-quark, and light parton jets. These techniques are applied to a search for inclusive H→bb¯ and H→cc¯ decays using a LHCb dataset corresponding to an integrated luminosity of 1.6 fb−1. The observed (expected) 95% confidence level upper limits correspond to 6.6 (11.1) times the SM cross-section for the H→bb¯ process, and 1003 (1834) times the SM cross-section for the H→cc¯ process.

AB - Two machine learning techniques for jet measurements at the LHCb experiment are presented: a regression-based method for jet-energy calibration and a deep neural network algorithm for jet flavour tagging, distinguishing between b-quark, c-quark, and light parton jets. These techniques are applied to a search for inclusive H→bb¯ and H→cc¯ decays using a LHCb dataset corresponding to an integrated luminosity of 1.6 fb−1. The observed (expected) 95% confidence level upper limits correspond to 6.6 (11.1) times the SM cross-section for the H→bb¯ process, and 1003 (1834) times the SM cross-section for the H→cc¯ process.

KW - Hadron-Hadron Scattering

KW - Higgs Physics

KW - Jet Physics

KW - Jets

UR - https://www.scopus.com/pages/publications/105047889139

U2 - 10.1007/JHEP07(2026)276

DO - 10.1007/JHEP07(2026)276

M3 - Artículo

AN - SCOPUS:105047889139

SN - 1029-8479

VL - 2026

JO - Journal of High Energy Physics

JF - Journal of High Energy Physics

IS - 7

M1 - 276

ER -

Machine learning techniques for jet reconstruction at LHCb and application to the search for H→bb¯ and H→cc¯ in s=13 TeV pp collisions

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this