[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126992-en":3,"doc-seo-126992-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126992,687207024643,"Oliver","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Machine Learning in High Energy Physics - A review of heavy-flavor jet tagging at the LHC","Machine learning has rapidly expanded in high energy physics, with a focused emphasis on heavy-flavor jet tagging in Large Hadron Collider experiments. This review surveys both legacy and modern ML methods, detailing data representation choices and model architectures ranging from traditional machine learning to deep learning. It highlights successful applications in the ATLAS and CMS experiments, including attention-based graph neural networks, and organizes algorithm development across the LHC’s three run periods into three generations.","Machine Learning in High Energy Physics: A review of heavy-flavor jet  \ntagging at the LHC  \nSpandan Mondal ∗ Luca Mastrolorenzo §  \narXiv :2404 .0 107 1v 1 [hep-ex] 1 Apr 2024  \nAbstract  \nThe application of machine learning (ML) in high energy physics (HEP), specifically in heavy-flavor jet tagging at Large Hadron Collider (LHC) experiments, has experienced remarkable growth and innovation in the past decade. This review provides a detailed examination of current and past ML techniques in this domain.  \nIt starts by exploring various data representation methods and ML architectures, encompassing traditional ML algorithms and advanced deep learning techniques. Subsequent sections discuss specific instances of successful ML applications in jet flavor tagging in the ATLAS and CMS experiments at the LHC, ranging from basic fullyconnected layers to graph neural networks employing attention mechanisms. To systematically categorize the advancements over the LHC’s three runs, the paper classifies jet tagging algorithms into three generations, each characterized by specific data representation techniques and ML architectures. This classification aims to provide an overview of the chronological evolution in this field. Finally, a brief discussion about anticipated future developments and potential research directions in the field is presented.  \n1 Introduction  \nThe task of jet identification in hadron collider experiments has seen steady development over the past decades. In particular, machine learning (ML) has revolutionized the way we view and  \n∗ Brown University, Providence, RI, USA.  \n§ Ex-member, CMS Experiment, CERN.  \nleverage various observables associated with a jet and its constituents. A jet refers to a collimated spray of particles that originate from a highenergy collision. They may originate either from a single quark/gluon generated in the hard scattering or from a hadronically-decaying Lorentzboosted heavy particle. While viewing the jet asa single object gives us only limited information about the particle initiating the jet, looking at its constituents provides us with additional information that can be used to predict the type of the initiating particle. Several approaches have been developed for this purpose over the past decades and these approaches are generally referred to as jet tagging.  \nTo analyze collision data in search for an interesting physics process (signal), one usually chooses a particular jet reconstruction strategy, along with a particular jet tagging algorithm (when necessary), depending on the expected features of the final state. For example, if the process involves the production of a hadronically-decaying heavy particle (such as W, Z, or Higgs boson, or a top quark) with a large transverse momentum (pT ≳ 250 GeV), one might use a so-called large-radius “fat”jet to reconstruct the entire decay within the jet radius. Such jets are usually characterized by a multi-pronged structure. Jet substructure techniques, and more recently ML-based classification algorithms, have been developed to distinguish fat jets arising from the aforementioned interesting heavy particle decays, from those arising from other physics processes (backgrounds), such as a gluon splitting into a pair of quarks. On the other hand, if the process generates one or more quarks/gluons that are spatially isolated, the event can be reconstructed using one or more small-radius “thin” jets. This is usually followed by application of techniques to identify the “fla-  \nvor” of the quark (up, down, strange, charm, bottom) or gluon that initiated the jet. This approach of identifying jet flavor is referred to as flavor tagging. The term flavor tagging can also be extended to specific use cases involving fat jets, for example, in the context of identifying heavy particles that decay into pairs of heavyflavor quarks (bottom quark-antiquark pair, b, or charm quark-antiquark pair, c) . For the rest of this paper, up, down, strange, charm","cbCaioWNdrxw4S3p","https://ap.wps.com/l/cbCaioWNdrxw4S3p","pdf",799611,1,38,"English","en",105,"# Introduction\n## Jet identification and tagging\n## Flavor tagging and heavy-flavor signatures\n## ML techniques and model architectures\n## Jet-tagging algorithm generations and outlook","[{\"question\":\"What is heavy-flavor jet tagging at the LHC?\",\"answer\":\"It is the use of jet-level information to identify whether a jet originated from heavy-flavor quarks (bottom or charm) rather than light flavors or gluons, leveraging signatures such as displaced tracks and secondary vertices.\"},{\"question\":\"How does the review organize ML progress over the LHC programs?\",\"answer\":\"It classifies jet tagging algorithms into three generations, each tied to specific data representation techniques and ML architectures, to reflect chronological evolution across the LHC’s three runs.\"},{\"question\":\"Which experiments and ML model types are discussed?\",\"answer\":\"The review discusses successful ML applications in ATLAS and CMS, covering approaches from fully connected layer-based models to graph neural networks with attention mechanisms.\"}]","Machine Learning in High Energy Physics - A review of heavy-flavor jet tagging at the LHC | PDF",1785936076,96,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-in-high-energy-physics-a-review-of-heavy-flavor-jet-tagging-at-the-lhc","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-in-high-energy-physics-a-review-of-heavy-flavor-jet-tagging-at-the-lhc/126992/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is heavy-flavor jet tagging at the LHC?","Question",{"text":75,"@type":76},"It is the use of jet-level information to identify whether a jet originated from heavy-flavor quarks (bottom or charm) rather than light flavors or gluons, leveraging signatures such as displaced tracks and secondary vertices.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the review organize ML progress over the LHC programs?",{"text":80,"@type":76},"It classifies jet tagging algorithms into three generations, each tied to specific data representation techniques and ML architectures, to reflect chronological evolution across the LHC’s three runs.",{"name":82,"@type":73,"acceptedAnswer":83},"Which experiments and ML model types are discussed?",{"text":84,"@type":76},"The review discusses successful ML applications in ATLAS and CMS, covering approaches from fully connected layer-based models to graph neural networks with attention mechanisms.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]