% 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{Krause:625593,
      author       = {Krause, Claudius and Faucci Giannelli, Michele and
                      Kasieczka, Gregor and Nachman, Benjamin and Salamani, Dalila
                      and Shih, David and Zaborowska, Anna and Amram, Oz and
                      Borras, Kerstin and Buckley, Matthew R. and Buhmann, Erik
                      and Buss, Thorsten and Da Costa Cardoso, Renato Paulo and
                      Caterini, Anthony L. and Chernyavskaya, Nadezda and Corchia,
                      Federico A. G. and Cresswell, Jesse C. and Diefenbacher,
                      Sascha and Dreyer, Etienne and Ekambaram, Vijay and Eren,
                      Engin and Ernst, Florian and Favaro, Luigi and Franchini,
                      Matteo and Gaede, Frank and Gross, Eilam and Hsu, Shih-Chieh
                      and Jaruskova, Kristina and Käch, Benno and Kalagnanam,
                      Jayant and Kansal, Raghav and Kim, Taewoo and Kobylianskii,
                      Dmitrii and Korol, Anatolii and Korcari, William and
                      Krücker, Dirk and Krüger, Katja and Letizia, Marco and Li,
                      Shu and Liu, Qibin and Liu, Xiulong and Loaiza-Ganem,
                      Gabriel and Madula, Thandikire and McKeown, Peter and
                      Melzer-Pellmann, Isabell-A. and Mikuni, Vinicius and Nguyen,
                      Nam and Ore, Ayodele and Palacios Schweitzer, Sofia and
                      Pang, Ian and Pedro, Kevin and Plehn, Tilman and Pokorski,
                      Witold and Qu, Huilin and Raikwar, Piyush and Raine, John A.
                      and Reyes-Gonzalez, Humberto and Rinaldi, Lorenzo and Ross,
                      Brendan Leigh and Scham, Moritz A. W. and Schnake, Simon
                      Patrik and Shimmin, Chase and Shlizerman, Eli and Soybelman,
                      Nathalie and Srivatsa, Mudhakar and Tsolaki, Kalliopi and
                      Vallecorsa, Sofia and Yeo, Kyongmin and Zhang, Rui},
      title        = {{C}alo{C}hallenge 2022: {A} {C}ommunity {C}hallenge for
                      {F}ast {C}alorimeter {S}imulation},
      reportid     = {PUBDB-2025-01144, arXiv:2410.21611. HEPHY-ML-24-05.
                      FERMILAB-PUB-24-0728-CMS. TTK-24-43},
      year         = {2024},
      note         = {204 pages, 100+ figures, 30+ tables},
      abstract     = {We present the results of the 'Fast Calorimeter Simulation
                      Challenge 2022' - the CaloChallenge. We study
                      state-of-the-art generative models on four calorimeter
                      shower datasets of increasing dimensionality, ranging from a
                      few hundred voxels to a few tens of thousand voxels. The 31
                      individual submissions span a wide range of current popular
                      generative architectures, including Variational AutoEncoders
                      (VAEs), Generative Adversarial Networks (GANs), Normalizing
                      Flows, Diffusion models, and models based on Conditional
                      Flow Matching. We compare all submissions in terms of
                      quality of generated calorimeter showers, as well as shower
                      generation time and model size. To assess the quality we use
                      a broad range of different metrics including differences in
                      1-dimensional histograms of observables, KPD/FPD scores,
                      AUCs of binary classifiers, and the log-posterior of a
                      multiclass classifier. The results of the CaloChallenge
                      provide the most complete and comprehensive survey of
                      cutting-edge approaches to calorimeter fast simulation to
                      date. In addition, our work provides a uniquely detailed
                      perspective on the important problem of how to evaluate
                      generative models. As such, the results presented here
                      should be applicable for other domains that use generative
                      AI and require fast and faithful generation of samples in a
                      large phase space.},
      cin          = {CMS},
      cid          = {I:(DE-H253)CMS-20120731},
      pnm          = {611 - Fundamental Particles and Forces (POF4-611) / DFG
                      project G:(GEPRIS)396021762 - TRR 257: Phänomenologische
                      Elementarteilchenphysik nach der Higgs-Entdeckung
                      (396021762) / DFG project G:(GEPRIS)390833306 - EXC 2121:
                      Quantum Universe (390833306)},
      pid          = {G:(DE-HGF)POF4-611 / G:(GEPRIS)396021762 /
                      G:(GEPRIS)390833306},
      experiment   = {EXP:(DE-MLZ)NOSPEC-20140101},
      typ          = {PUB:(DE-HGF)25},
      eprint       = {2410.21611},
      howpublished = {arXiv:2410.21611},
      archivePrefix = {arXiv},
      SLACcitation = {$\%\%CITATION$ = $arXiv:2410.21611;\%\%$},
      url          = {https://bib-pubdb1.desy.de/record/625593},
}