The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider

Simple item page
dc.citation.articleNumber043en_US
dc.citation.journalTitleSciPost Physicsen_US
dc.citation.volumeNumber12en_US
dc.contributor.authorAarrestad, Theaen_US
dc.contributor.authorvan Beekveld, Melissaen_US
dc.contributor.authorBona, Marcellaen_US
dc.contributor.authorBoveia, Antonioen_US
dc.contributor.authorCaron, Saschaen_US
dc.contributor.authorDavies, Joeen_US
dc.contributor.authorde Simone, Andreaen_US
dc.contributor.authorDoglioni, Caterinaen_US
dc.contributor.authorDuarte, Javieren_US
dc.contributor.authorFarbin, Amiren_US
dc.contributor.authorGupta, Honeyen_US
dc.contributor.authorHendriks, Lucen_US
dc.contributor.authorHeinrich, Lukas A.en_US
dc.contributor.authorHowarth, Jamesen_US
dc.contributor.authorJawahar, Pratiken_US
dc.contributor.authorJueid, Adilen_US
dc.contributor.authorLastow, Jessicaen_US
dc.contributor.authorLeinweber, Adamen_US
dc.contributor.authorMamuzic, Juditaen_US
dc.contributor.authorMerényi, Erzsébeten_US
dc.contributor.authorMorandini, Alessandroen_US
dc.contributor.authorMoskvitina, Polinaen_US
dc.contributor.authorNellist, Claraen_US
dc.contributor.authorNgadiuba, Jenniferen_US
dc.contributor.authorOstdiek, Bryanen_US
dc.contributor.authorPierini, Maurizioen_US
dc.contributor.authorRavina, Baptisteen_US
dc.contributor.authorRuiz de Austri, Robertoen_US
dc.contributor.authorSekmen, Sezenen_US
dc.contributor.authorTouranakou, Maryen_US
dc.contributor.authorVaškeviciute, Marijaen_US
dc.contributor.authorVilalta, Ricardoen_US
dc.contributor.authorVlimant, Jean-Rochen_US
dc.contributor.authorVerheyen, Roben_US
dc.contributor.authorWhite, Martinen_US
dc.contributor.authorWulff, Ericen_US
dc.contributor.authorWallin, Eriken_US
dc.contributor.authorWozniak, Kinga A.en_US
dc.contributor.authorZhang, Zhongyien_US
dc.date.accessioned2022-03-24T13:31:36Zen_US
dc.date.available2022-03-24T13:31:36Zen_US
dc.date.issued2022en_US
dc.description.abstractWe describe the outcome of a data challenge conducted as part of the Dark Machines Initiative and the Les Houches 2019 workshop on Physics at TeV colliders. The challenged aims at detecting signals of new physics at the LHC using unsupervised machine learning algorithms. First, we propose how an anomaly score could be implemented to define model-independent signal regions in LHC searches. We define and describe a large benchmark dataset, consisting of >1 Billion simulated LHC events corresponding to 10 fb−110 fb−1 of proton-proton collisions at a center-of-mass energy of 13 TeV. We then review a wide range of anomaly detection and density estimation algorithms, developed in the context of the data challenge, and we measure their performance in a set of realistic analysis environments. We draw a number of useful conclusions that will aid the development of unsupervised new physics searches during the third run of the LHC, and provide our benchmark dataset for future studies at https://www.phenoMLdata.org. Code to reproduce the analysis is provided at https://github.com/bostdiek/DarkMachines-UnsupervisedChallenge.en_US
dc.identifier.citationAarrestad, Thea, van Beekveld, Melissa, Bona, Marcella, et al.. "The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider." <i>SciPost Physics,</i> 12, (2022) SciPost Foundation: https://doi.org/10.21468/SciPostPhys.12.1.043.en_US
dc.identifier.digitalSciPostPhys_12_1_043en_US
dc.identifier.doihttps://doi.org/10.21468/SciPostPhys.12.1.043en_US
dc.identifier.urihttps://hdl.handle.net/1911/112034en_US
dc.language.isoengen_US
dc.publisherSciPost Foundationen_US
dc.rightsThis work is licensed under the Creative Commons Attribution 4.0 International License.en_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.titleThe Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collideren_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SciPostPhys_12_1_043.pdf
Size:
2.36 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
Statistics Publications