{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T04:36:28Z","timestamp":1793853388347,"version":"4.6.1"},"reference-count":55,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"content-version":"vor","delay-in-days":20,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"content-version":"tdm","delay-in-days":20,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["EXC-2094-390783311"],"award-info":[{"award-number":["EXC-2094-390783311"]}],"id":[{"id":"10.13039\/501100001659","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":[[2024,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    In this work we demonstrate that significant gains in performance and data efficiency can be achieved in High Energy Physics (HEP) by moving beyond the standard paradigm of sequential optimization or reconstruction and analysis components. We conceptually connect HEP reconstruction and analysis to modern machine learning workflows such as pretraining, finetuning, domain adaptation and high-dimensional embedding spaces and quantify the gains in the example usecase of searches of heavy resonances decaying via an intermediate di-Higgs system to four\n                    <jats:italic>b<\/jats:italic>\n                    -jets. To our knowledge this is the first example of a low-level feature extraction network finetuned for a downstream HEP analysis objective.\n                  <\/jats:p>","DOI":"10.1088\/2632-2153\/ad55a3","type":"journal-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T18:42:11Z","timestamp":1717785731000},"page":"025075","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Finetuning foundation models for joint analysis optimization in High Energy Physics"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2281-3822","authenticated-orcid":true,"given":"Matthias","family":"Vigl","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9111-4916","authenticated-orcid":true,"given":"Nicole","family":"Hartman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4048-7584","authenticated-orcid":false,"given":"Lukas","family":"Heinrich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,6,21]]},"reference":[{"key":"mlstad55a3bib1","first-page":"pp 59","article-title":"Deep learning from four vectors","author":"Baldi","year":"2022"},{"key":"mlstad55a3bib2","first-page":"pp 313","article-title":"End-to-end analyses using image classification","author":"Aurisano","year":"2022"},{"key":"mlstad55a3bib3","doi-asserted-by":"publisher","first-page":"JHEP01(2019)057","DOI":"10.1007\/JHEP01(2019)057","article-title":"QCD-aware recursive neural networks for jet physics","author":"Louppe","year":"2019","journal-title":"J. High Energy Phys."},{"key":"mlstad55a3bib4","first-page":"pp 387","article-title":"Graph neural networks for particle tracking and reconstruction","author":"Duarte","year":"2022"},{"key":"mlstad55a3bib5","article-title":"Hierarchical graph neural networks for particle track reconstruction","author":"Liu","year":"2023"},{"key":"mlstad55a3bib6","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s41781-021-00073-z","article-title":"Charged particle tracking via edge-classifying interaction networks","volume":"5","author":"DeZoort","year":"2021","journal-title":"Comput. Softw. Big Sci."},{"key":"mlstad55a3bib7","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1140\/epjc\/s10052-021-09158-w","article-title":"MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks","volume":"81","author":"Pata","year":"2021","journal-title":"Eur. Phys. J. C"},{"key":"mlstad55a3bib8","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1140\/epjc\/s10052-023-11677-7","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":"mlstad55a3bib9","article-title":"Differentiable vertex fitting for jet flavour tagging","author":"Smith","year":"2023"},{"key":"mlstad55a3bib10","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.cpc.2019.06.007","article-title":"INFERNO: inference-aware neural optimisation","volume":"244","author":"De Castro","year":"2019","journal-title":"Comput. Phys. Commun."},{"key":"mlstad55a3bib11","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2438\/1\/012105","article-title":"neos: end-to-end-optimised summary statistics for High Energy Physics","volume":"2438","author":"Simpson","year":"2023","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstad55a3bib12","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1169739","article-title":"pyhf: v0.7.5","author":"Heinrich","year":"2024"},{"key":"mlstad55a3bib13","doi-asserted-by":"publisher","first-page":"2823","DOI":"10.21105\/joss.02823","article-title":"pyhf: pure-Python implementation of HistFactory statistical models","volume":"6","author":"Heinrich","year":"2021","journal-title":"J. Open Source Softw."},{"key":"mlstad55a3bib14","article-title":"Branches of a tree: taking derivatives of programs with discrete and branching randomness in High Energy Physics","author":"Kagan","year":"2023"},{"key":"mlstad55a3bib15","article-title":"Morphing parton showers with event derivatives","author":"Nachman","year":"2022"},{"key":"mlstad55a3bib16","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2438\/1\/012137","article-title":"Differentiable matrix elements with MadJax","volume":"2438","author":"Heinrich","year":"2023","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstad55a3bib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.revip.2023.100085","article-title":"Toward the end-to-end optimization of particle physics instruments with differentiable programming","volume":"10","author":"MODE","year":"2023","journal-title":"Rev. Phys."},{"key":"mlstad55a3bib18","doi-asserted-by":"publisher","first-page":"014","DOI":"10.21468\/SciPostPhys.7.1.014","article-title":"The machine learning landscape of top taggers","volume":"7","author":"Kasieczka","year":"2019","journal-title":"SciPost Phys."},{"key":"mlstad55a3bib19","doi-asserted-by":"publisher","first-page":"JHEP01(2019)121","DOI":"10.1007\/JHEP01(2019)121","article-title":"Energy flow networks: deep sets for particle jets","author":"Komiske","year":"2019","journal-title":"J. High Energy Phys."},{"key":"mlstad55a3bib20","article-title":"Particle transformer for jet tagging","author":"Qu","year":"2022"},{"key":"mlstad55a3bib21","doi-asserted-by":"publisher","first-page":"188","DOI":"10.21468\/SciPostPhys.12.6.188","article-title":"Symmetries, safety and self-supervision","volume":"12","author":"Dillon","year":"2022","journal-title":"SciPost Phys."},{"key":"mlstad55a3bib22","doi-asserted-by":"publisher","first-page":"JHEP07(2022)030","DOI":"10.1007\/JHEP07(2022)030","article-title":"An efficient Lorentz equivariant graph neural network for jet tagging","author":"Gong","year":"2022","journal-title":"J. High Energy Phys."},{"key":"mlstad55a3bib23","article-title":"Transformer neural networks for identifying boosted Higgs bosons decaying into bb\u00af and cc\u00af in ATLAS","author":"ATLAS Collaboration","year":"2023"},{"key":"mlstad55a3bib24","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2022"},{"key":"mlstad55a3bib25","article-title":"DINOv2: learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"mlstad55a3bib26","article-title":"VICReg: variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2021"},{"key":"mlstad55a3bib27","article-title":"BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019"},{"key":"mlstad55a3bib28","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"mlstad55a3bib29","article-title":"GPT-4 technical report","author":"OpenAI","year":"2023"},{"key":"mlstad55a3bib30","first-page":"pp 1877","article-title":"Language models are few-shot learners","volume":"vol 33","author":"Brown","year":"2020"},{"key":"mlstad55a3bib31","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"mlstad55a3bib32","article-title":"Radio galaxy zoo: towards building the first multi-purpose foundation model for radio astronomy with self-supervised learning","author":"Slijepcevic","year":"2023"},{"key":"mlstad55a3bib33","article-title":"AstroCLIP: cross-modal pre-training for astronomical foundation models","author":"Lanusse","year":"2023"},{"key":"mlstad55a3bib34","article-title":"Towards a foundation model for neural network wavefunctions","author":"Scherbela","year":"2023"},{"key":"mlstad55a3bib35","article-title":"HyenaDNA: long-range genomic sequence modeling at single nucleotide resolution","author":"Nguyen","year":"2023"},{"key":"mlstad55a3bib36","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1140\/epjc\/s10052-022-10469-9","article-title":"Leveraging universality of jet taggers through transfer learning","volume":"82","author":"Dreyer","year":"2022","journal-title":"Eur. Phys. J. C"},{"key":"mlstad55a3bib37","article-title":"Masked particle modeling on sets: towards self-supervised High Energy Physics foundation models","author":"Heinrich","year":"2024"},{"key":"mlstad55a3bib38","doi-asserted-by":"publisher","first-page":"30055","DOI":"10.1073\/pnas.1912789117","article-title":"The frontier of simulation-based inference","volume":"117","author":"Cranmer","year":"2020","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstad55a3bib39","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2438\/1\/012100","article-title":"Machine learning for particle flow reconstruction at CMS","volume":"2438","author":"CMS","year":"2023","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstad55a3bib40","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1140\/epjc\/s10052-021-09675-8","article-title":"Performance of a geometric deep learning pipeline for HL-LHC particle tracking","volume":"81","author":"Exa.TrkX","year":"2021","journal-title":"Eur. Phys. J. C"},{"key":"mlstad55a3bib41","doi-asserted-by":"publisher","first-page":"JHEP03(2011)015","DOI":"10.1007\/JHEP03(2011)015","article-title":"Identifying boosted objects with N-subjettiness","author":"Thaler","year":"2011","journal-title":"J. High Energy Phys."},{"key":"mlstad55a3bib42","volume":"vol 958","author":"Marzani","year":"2019"},{"key":"mlstad55a3bib43","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.6619768","article-title":"JetClass: a large-scale dataset for deep learning in jet physics","author":"Qu","year":"2022"},{"key":"mlstad55a3bib44","doi-asserted-by":"publisher","first-page":"JHEP04(2008)063","DOI":"10.1088\/1126-6708\/2008\/04\/063","article-title":"The anti-kt jet clustering algorithm","author":"Cacciari","year":"2008","journal-title":"J. High Energy Phys."},{"key":"mlstad55a3bib45","doi-asserted-by":"publisher","first-page":"JHEP07(2014)079","DOI":"10.1007\/JHEP07(2014)079","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 Energy Phys."},{"key":"mlstad55a3bib46","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1016\/j.cpc.2008.01.036","article-title":"A brief introduction to PYTHIA 8.1","volume":"178","author":"Sj\u00f6strand","year":"2008","journal-title":"Comput. Phys. Commun."},{"key":"mlstad55a3bib47","doi-asserted-by":"publisher","first-page":"JHEP02(2014)057","DOI":"10.1007\/JHEP02(2014)057","article-title":"DELPHES 3, a modular framework for fast simulation of a generic collider experiment","author":"DELPHES 3","year":"2014","journal-title":"J. High Energy Phys."},{"key":"mlstad55a3bib48","doi-asserted-by":"publisher","DOI":"10.7483\/OPENDATA.CMS.JGJX.MS7Q","article-title":"Sample with jet, track and secondary vertex properties for Hbb tagging ML studies","author":"Javier","year":"2019"},{"key":"mlstad55a3bib49","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41597-021-01109-0","article-title":"A FAIR and AI-ready Higgs boson decay dataset","volume":"9","author":"Chen","year":"2021","journal-title":"Sci. Data"},{"key":"mlstad55a3bib50","article-title":"Deep sets","author":"Zaheer","year":"2017"},{"key":"mlstad55a3bib51","doi-asserted-by":"publisher","first-page":"JHEP05(2014)146","DOI":"10.1007\/JHEP05(2014)146","article-title":"Soft drop","author":"Larkoski","year":"2014","journal-title":"J. High Energy Phys."},{"key":"mlstad55a3bib52","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW59228.2023.00390","article-title":"Disentangling neuron representations with concept vectors","author":"O\u2019Mahony","year":"2023"},{"key":"mlstad55a3bib53","article-title":"Lookahead optimizer: k steps forward, 1 step back","volume":"vol 32","author":"Zhang","year":"2019"},{"key":"mlstad55a3bib54","article-title":"On the variance of the adaptive learning rate and beyond","author":"Liu","year":"2021"},{"key":"mlstad55a3bib55","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T06:27:46Z","timestamp":1718951266000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad55a3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,1]]},"references-count":55,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6,21]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad55a3","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,1]]},"assertion":[{"value":"Finetuning foundation models for joint analysis optimization in High Energy 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 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-02-28","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}