% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Aad:629230,
      author       = {Aad, Georges and others},
      collaboration = {{ATLAS Collaboration}},
      title        = {{T}ransforming jet flavour tagging at {ATLAS}},
      reportid     = {PUBDB-2025-01770, arXiv:2505.19689. CERN-EP-2025-103},
      year         = {2025},
      note         = {All figures including auxiliary figures are available at
                      https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PAPERS/FTAG-2023-05/.
                      Submitted to: Nature Communications},
      abstract     = {Jet flavour tagging enables the identification of jets
                      originating from heavy-flavour quarks in proton-proton
                      collisions at the Large Hadron Collider, playing a critical
                      role in its physics programmes. This paper presents GN2, a
                      novel transformer-based flavour tagging algorithm deployed
                      by the ATLAS Collaboration that represents a paradigm shift
                      from previous approaches. Designed to classify jets based on
                      the flavour of their constituent particles, GN2 processes
                      low-level tracking information in an end-to-end architecture
                      and incorporates physics-informed auxiliary training
                      objectives to enhance both interpretability and performance.
                      Its performance is validated in both simulation and
                      collision data. The GN2 algorithm provides substantial
                      benefits for physics analyses involving heavy-flavour jets,
                      such as measurements of Higgs boson pair production and the
                      couplings of bottom and charm quarks to the Higgs boson, and
                      demonstrates the impact of advanced machine learning methods
                      in experimental particle physics.},
      cin          = {ATLAS},
      cid          = {I:(DE-H253)ATLAS-20120731},
      pnm          = {611 - Fundamental Particles and Forces (POF4-611) / DFG
                      project G:(GEPRIS)469666862 - Präzisionstests des
                      Standardmodells unter der Verwendung von geboosteten
                      W/Z-Bosonen am Large Hadron Collider (469666862) / REALDARK
                      - REAL-time discovery strategies for DARK matter and dark
                      sector signals at the ATLAS detector with Run-3 LHC data
                      (101002463) / DITTO - Comprehensive search for new phenomena
                      in the dilepton spectrum at the LHC (101089007) / BARD -
                      B-resonance Algorithm using Rare Decays (101116429)},
      pid          = {G:(DE-HGF)POF4-611 / G:(GEPRIS)469666862 /
                      G:(EU-Grant)101002463 / G:(EU-Grant)101089007 /
                      G:(EU-Grant)101116429},
      experiment   = {EXP:(DE-H253)LHC-Exp-ATLAS-20150101},
      typ          = {PUB:(DE-HGF)25},
      eprint       = {2505.19689},
      howpublished = {arXiv:2505.19689},
      archivePrefix = {arXiv},
      SLACcitation = {$\%\%CITATION$ = $arXiv:2505.19689;\%\%$},
      doi          = {10.3204/PUBDB-2025-01770},
      url          = {https://bib-pubdb1.desy.de/record/629230},
}