[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124568-en":3,"doc-seo-124568-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},124568,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Machine Learning in Top Physics in the ATLAS and CMS Collaborations","Machine learning is a key tool in many analyses of top-quark physics within the ATLAS and CMS Collaborations. The work provides a concise overview of current ML applications and highlights ongoing studies aimed at future use. It summarizes how ML methods are applied to top-related tasks, with emphasis on constructing observables for improved signal–background separation and increased statistical power, illustrated with an example from each collaboration and a selection of active projects.","CR-2023/006 January 24, 2023  \nMachine Learning in Top Physics in the ATLAS and CMS  \nCollaborations  \narXiv :2301 .09534v1 [hep-ex] 23 Jan 2023  \nPhilip Keicher 1  \nInstitute of Experimental Physics University of Hamburg, D-22761 Hamburg, GERMANY  \nMachine learning is essential in many aspects of top-quark related physics in the ATLAS and CMS Collaborations. This work aims to give a brief overview over current applications in the two collaborations as well as on-going studies for future applications.  \nPRESENTED AT  \n15th International Workshop on Top Quark Physics  \nDurham, UK, 4{9 September, 2022  \n1Work supported by the Ministry for Education and Research (BMBF) .  \nCopyright 2023 CERN for the bene􀀌t of the ATLAS and CMS Collaborations. Reproduction of this article or parts of it is allowed as speci􀀌ed in the CC-BY-4.0 license  \n1 Introduction  \nMachine learning (ML) applications are nowadays well-established tools in modern data science problems. An increasing number of techniques and analyses in highenergy physics are harnessing the capabilities of these methods. Many of these applications within the community are related to the top quark due to its rich phenomenology within both the standard model of particle physics (SM) and beyond. Most of these applications for top quark physics within the ATLAS [1] and CMS [2] Collaborations can be separated according to three paradigms. First, ML applications are used as tagging algorithms to identify top quarks. Second, ML is used to reconstruct top quark properties. Finally, ML is used to construct observables that have a strong separation of signal and background processes, thus further increasing the statistical power of analyses. Some select examples of the usage of ML techniques in these 􀀌elds within both ATLAS and CMS Collaborations can be found in the references of this work.  \nThis work focuses on the last 􀀌eld of applications described above. Speci􀀌cally, the ML usage of an example from each collaboration and a summary of select ongoing projects is presented. For a more thorough review of the analyses, please refer to Refs. [3, 4] .  \n2 Machine learning for a probe of EFT operators in the associated production of top quarks with a Z boson at the CMS experiment  \nThe search for physics beyond the SM is crucial to increase our knowledge of the fundamental mechanisms of particle physics. For this purpose, e􀀋ective 􀀌eld theories (EFTs) have proven themselves as a promising tool. Their general concept is to extend the known Lagrange function L with additional operators O such that  \nL = LSM +  Xi ~~ ~~c􀀃~~i~~d()4 Oi(d):  \nIn this equation, d refers to the dimension of the operators, N denotes the maximum dimension of additional operators considered and 􀀃 denotes the energy scale for new physics. The parameters ci are known as the Wilson coe􀀎cients and indicate the contribution of the corresponding operator to the extension of the SM Lagrangian LSM .  \nThe CMS analysis described in Ref. [3] probes these coe􀀎cients in the context of the production of top quarks in association with Z bosons. To this end, the analysis considers three signal processes that are sensitive to a di􀀋erent variety of operators:  \nFigure 1: Events are 􀀌rst categorized according to three classes within the SM (top left) . Events classi􀀌ed as either tZq or ttZ are then considered for a binary classi􀀌 -cation to increase the sensitivity to EFT contributions (bottom left) . The resulting distributions are expected to be sensitive to di􀀋erent values of the corresponding Wilson coe􀀎cients (right) . Figure adapted from Ref. [3] .  \nthe production of a top quark-antiquark pair in association with a Z boson (ttZ) as well as the production of a single top quark in association with a Z boson and a W boson (tZW) or an additional jet (tZq) . The analysis de􀀌nes two signal regions based on the number of leptons in the 􀀌nal state as well as additional control regions designed to control the dominant background processes","cbCaisDKYm4xmBiw","https://ap.wps.com/l/cbCaisDKYm4xmBiw","pdf",1145955,1,"English","en",105,"# Introduction\n# Machine learning for a probe of EFT operators in associated production of top quarks with a Z boson at CMS","[{\"question\":\"What is the main goal of this work on machine learning in top-quark physics?\",\"answer\":\"To provide a brief overview of current ML applications in ATLAS and CMS and to summarize ongoing studies for future applications, with emphasis on how ML improves observables and signal–background separation.\"},{\"question\":\"How are ML applications commonly organized for top-quark physics in ATLAS and CMS?\",\"answer\":\"They are grouped into three paradigms: tagging top quarks, reconstructing top-quark properties, and building observables that enhance separation between signal and background to increase statistical power.\"},{\"question\":\"In the CMS example, what does the ML approach do to probe EFT effects?\",\"answer\":\"It first categorizes events using a multi-classification network based on kinematic variables and b-tagging discriminants, then uses the ML strategy to target EFT contributions through interference effects with the Standard Model.\"}]","Machine Learning in Top Physics in the ATLAS and CMS Collaborations | PDF",1785893024,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"machine-learning-in-top-physics-in-the-atlas-and-cms-collaborations","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/machine-learning-in-top-physics-in-the-atlas-and-cms-collaborations/124568/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of this work on machine learning in top-quark physics?","Question",{"text":74,"@type":75},"To provide a brief overview of current ML applications in ATLAS and CMS and to summarize ongoing studies for future applications, with emphasis on how ML improves observables and signal–background separation.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How are ML applications commonly organized for top-quark physics in ATLAS and CMS?",{"text":79,"@type":75},"They are grouped into three paradigms: tagging top quarks, reconstructing top-quark properties, and building observables that enhance separation between signal and background to increase statistical power.",{"name":81,"@type":72,"acceptedAnswer":82},"In the CMS example, what does the ML approach do to probe EFT effects?",{"text":83,"@type":75},"It first categorizes events using a multi-classification network based on kinematic variables and b-tagging discriminants, then uses the ML strategy to target EFT contributions through interference effects with the Standard Model.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]