{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T10:41:49Z","timestamp":1761302509059,"version":"build-2065373602"},"reference-count":38,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001742","name":"United States-Israel Binational Science Foundation","doi-asserted-by":"crossref","award":["714179-2020780"],"award-info":[{"award-number":["714179-2020780"]}],"id":[{"id":"10.13039\/501100001742","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001658","name":"Minerva Foundation","doi-asserted-by":"crossref","award":["715027"],"award-info":[{"award-number":["715027"]}],"id":[{"id":"10.13039\/501100001658","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Weizmann Institute for Artificial Intelligence","award":["151676"],"award-info":[{"award-number":["151676"]}]},{"name":"National Science Foundation","award":["2120747"],"award-info":[{"award-number":["2120747"]}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"crossref","award":["DE-FOA-0002705"],"award-info":[{"award-number":["DE-FOA-0002705"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We extend the re-simulation-based self-supervised learning approach to learning representations of hadronic jets in colliders by exploiting the Markov property of the standard simulation chain. Instead of masking, cropping, or other forms of data augmentation, this approach simulates pairs of events where the initial portion of the simulation is shared, but the subsequent stages of the simulation evolve independently. When paired with a contrastive loss function, this naturally leads to representations that capture the physics in the initial stages of the simulation. In particular, we force the hard scattering and parton shower to be shared and let the hadronization and interaction with the detector evolve independently. We then evaluate the utility of these representations on downstream tasks.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae1100","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T22:51:51Z","timestamp":1759963911000},"page":"045015","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-supervised learning strategies for jet physics"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0290-0566","authenticated-orcid":true,"given":"Patrick","family":"Rieck","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5769-7094","authenticated-orcid":false,"given":"Kyle","family":"Cranmer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8955-9510","authenticated-orcid":true,"given":"Etienne","family":"Dreyer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1244-9350","authenticated-orcid":false,"given":"Eilam","family":"Gross","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2155-1859","authenticated-orcid":false,"given":"Nilotpal","family":"Kakati","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0070-5900","authenticated-orcid":true,"given":"Dmitrii","family":"Kobylianskii","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4737-3931","authenticated-orcid":false,"given":"Garrett W","family":"Merz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0209-0858","authenticated-orcid":true,"given":"Nathalie","family":"Soybelman","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"article-title":"A simple framework for contrastive learning of visual representations","year":"2020","author":"Chen","key":"mlstae1100bib1","type":"conference-proceedings"},{"article-title":"Chemberta: large-scale self-supervised pretraining for molecular property prediction","year":"2020","author":"Chithrananda","key":"mlstae1100bib2","type":"preprint"},{"article-title":"Climax: a foundation model for weather and climate","year":"2023","author":"Nguyen","key":"mlstae1100bib3","type":"preprint"},{"key":"mlstae1100bib4","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1093\/rasti\/rzad028","type":"journal-article","article-title":"A brief review of contrastive learning applied to astrophysics","volume":"2","author":"Huertas-Company","year":"2023","journal-title":"RAS Tech. Instrum."},{"key":"mlstae1100bib5","doi-asserted-by":"publisher","first-page":"188","DOI":"10.21468\/SciPostPhys.12.6.188","type":"journal-article","article-title":"Symmetries, safety and self-supervision","volume":"12","author":"Dillon","year":"2022","journal-title":"SciPost Phys."},{"key":"mlstae1100bib6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.111.032010","type":"journal-article","article-title":"Resimulation-based self-supervised learning for pretraining physics foundation models","volume":"111","author":"Harris","year":"2025","journal-title":"Phys. Rev. D"},{"article-title":"Particle transformer for jet tagging","year":"2022","author":"Qu","key":"mlstae1100bib7","type":"preprint"},{"article-title":"Transformer neural networks for identifying boosted Higgs Bosons decaying into bb\u00af and cc\u00af in ATLAS","year":"2023","author":"ATLAS Collaboration","key":"mlstae1100bib8","type":"other"},{"key":"mlstae1100bib9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.106.056005","type":"journal-article","article-title":"Self-supervised anomaly detection for new physics","volume":"106","author":"Dillon","year":"2022","journal-title":"Phys. Rev. D"},{"key":"mlstae1100bib10","doi-asserted-by":"publisher","first-page":"056","DOI":"10.21468\/SciPostPhysCore.7.3.056","type":"journal-article","article-title":"Anomalies, representations and self-supervision","volume":"7","author":"Dillon","year":"2024","journal-title":"SciPost Phys. Core"},{"key":"mlstae1100bib11","doi-asserted-by":"publisher","first-page":"042","DOI":"10.21468\/SciPostPhys.18.2.042","type":"journal-article","article-title":"Semi-visible jets, energy-based models and self-supervision","volume":"18","author":"Favaro","year":"2025","journal-title":"SciPost Phys."},{"article-title":"Anomaly preserving contrastive neural embeddings for end-to-end model-independent searches at the LHC","year":"2025","author":"Metzger","key":"mlstae1100bib12","type":"preprint"},{"article-title":"Large-scale pretraining and finetuning for efficient jet classification in particle physics","year":"2024","author":"Zhao","key":"mlstae1100bib13","type":"conference-proceedings"},{"key":"mlstae1100bib14","doi-asserted-by":"publisher","first-page":"4916","DOI":"10.1038\/s41467-024-49104-4","type":"journal-article","article-title":"Ultra-high-granularity detector simulation with intra-event aware generative adversarial network and self-supervised relational reasoning","volume":"15","author":"Hashemi","year":"2024","journal-title":"Nat. Commun."},{"key":"mlstae1100bib14","doi-asserted-by":"publisher","first-page":"5825","DOI":"10.1038\/s41467-024-49971-x","type":"journal-article","article-title":"Ultra-high-granularity detector simulation with intra-event aware generative adversarial network and self-supervised relational reasoning","volume":"15","author":"Hashemi","year":"2024","journal-title":"Nat. Commun."},{"article-title":"Pre-training strategy using real particle collision data for event classification in collider physics","year":"2023","author":"Kishimoto","key":"mlstae1100bib15","type":"conference-proceedings"},{"key":"mlstae1100bib16","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad64a8","type":"journal-article","article-title":"Masked particle modeling on sets: towards self-supervised high energy physics foundation models","volume":"5","author":"Golling","year":"2024","journal-title":"Mach. Learn. Sci. Technol."},{"article-title":"Is tokenization needed for masked particle modelling?","year":"2024","author":"Leigh","key":"mlstae1100bib17","type":"preprint"},{"key":"mlstae1100bib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.111.L051504","type":"journal-article","article-title":"Solving key challenges in collider physics with foundation models","volume":"111","author":"Mikuni","year":"2025","journal-title":"Phys. Rev. D"},{"article-title":"Bumblebee: foundation model for particle physics discovery","year":"2024","author":"Wildridge","key":"mlstae1100bib19","type":"conference-proceedings"},{"key":"mlstae1100bib20","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad66ad","type":"journal-article","article-title":"OmniJet-\u03b1: the first cross-task foundation model for particle physics","volume":"5","author":"Birk","year":"2024","journal-title":"Mach. Learn. Sci. Technol."},{"key":"mlstae1100bib21","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ade58f","type":"journal-article","article-title":"Aspen open jets: unlocking LHC data for foundation models in particle physics","volume":"6","author":"Amram","year":"2025","journal-title":"Mach. Learn. Sci. Tech."},{"key":"mlstae1100bib22","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.111.054015","type":"journal-article","article-title":"Method to simultaneously facilitate all jet physics tasks","volume":"111","author":"Mikuni","year":"2025","journal-title":"Phys. Rev. D"},{"key":"mlstae1100bib23","doi-asserted-by":"publisher","first-page":"JHEP07(2014)079","DOI":"10.1007\/JHEP07(2014)079","type":"journal-article","article-title":"The automated computation of tree-level and next-to-leading order differential cross sections and their matching to parton shower simulations","author":"Alwall","year":"2014","journal-title":"J. High Energ. Phys."},{"key":"mlstae1100bib24","doi-asserted-by":"publisher","first-page":"8","DOI":"10.21468\/SciPostPhysCodeb.8","type":"journal-article","article-title":"A comprehensive guide to the physics and usage of PYTHIA 8.3","author":"Bierlich","year":"2022","journal-title":"SciPost Phys. Codebases"},{"key":"mlstae1100bib25","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acf186","type":"journal-article","article-title":"Configurable calorimeter simulation for AI applications","volume":"4","author":"Charkin-Gorbulin","year":"2023","journal-title":"Mach. Learn. Sci. Tech."},{"key":"mlstae1100bib26","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/S0168-9002(03)01368-8","type":"journal-article","article-title":"Geant4 \u2013 a simulation toolkit","volume":"506","author":"Geant4 collaboration","year":"2003","journal-title":"Nucl. Instrum. Methods A"},{"key":"mlstae1100bib27","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/TNS.2006.869826","type":"journal-article","article-title":"Geant4 developments and applications","volume":"53","author":"Geant4 collaboration","year":"2006","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"mlstae1100bib28","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.nima.2016.06.125","type":"journal-article","article-title":"Recent developments in Geant4","volume":"835","author":"Charkin-Gorbulin","year":"2016","journal-title":"Nucl. Instrum. Methods A"},{"key":"mlstae1100bib29","doi-asserted-by":"publisher","first-page":"063","DOI":"10.1088\/1126-6708\/2008\/04\/063","type":"journal-article","article-title":"The anti-kt jet clustering algorithm","volume":"4","author":"Cacciari","year":"2008","journal-title":"JHEP"},{"article-title":"LoRA: low-rank adaptation of large language models","year":"2022","author":"Hu","key":"mlstae1100bib30","type":"conference-proceedings"},{"key":"mlstae1100bib31","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1140\/epjc\/s10052-025-14443-z","type":"journal-article","article-title":"HGPflow: extending hypergraph particle flow to collider event reconstruction","volume":"85","author":"Kakati","year":"2025","journal-title":"Eur. Phys. J. C"},{"article-title":"Adam: a method for stochastic optimization","year":"2014","author":"Kingma","key":"mlstae1100bib32","type":"preprint"},{"article-title":"Super-convergence: very fast training of neural networks using large learning rates","year":"2018","author":"Smith","key":"mlstae1100bib33","type":"preprint"},{"article-title":"Attention is all you need","year":"2017","author":"Vaswani","key":"mlstae1100bib34","type":"conference-proceedings"},{"key":"mlstae1100bib35","first-page":"128","type":"journal-article","article-title":"Search for resonant production of dark quarks in the dijet final state with the ATLAS detector","volume":"02","author":"Aad","year":"2024","journal-title":"J. High Energ. Phys."},{"key":"mlstae1100bib36","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1140\/epjc\/s10052-023-11677-7","type":"journal-article","article-title":"Reconstructing particles in jets using set transformer and hypergraph prediction networks","volume":"83","author":"Di Bello","year":"2023","journal-title":"Eur. Phys. J. C"},{"key":"mlstae1100bib37","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.15382841","type":"journal-article","article-title":"Quark, gluon, hadronic tau, and dark jets simulated with COCOA","author":"Rieck","year":"2025","journal-title":"Zenodo"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T10:36:53Z","timestamp":1761302213000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae1100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"references-count":38,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,10,24]]},"published-print":{"date-parts":[[2025,12,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae1100","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"Self-supervised learning strategies for jet physics","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-05-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}