[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118256-en":3,"doc-seo-118256-105":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},118256,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Top-philic Machine Learning - Review of Machine Learning Techniques for Top Quark Searches at the LHC","Top-philic Machine Learning reviews how modern machine learning methods strengthen searches for processes involving top quarks at the LHC. It revisits core ML formalisms including convolutional neural networks, graph neural networks, and attention mechanisms, linking them to improved top-tagging, top reconstruction, and event classification workflows. The review further covers likelihood-free inference and generative unfolding models, emphasizing their use in top-quark scenarios and the resulting gains for physics sensitivity and modeling.","arXiv :2407 .00 183v2 [hep-ph] 2 Jul 2024  \nEPJ manuscript No.  \n(will be inserted by the editor)  \nTop-philic Machine Learning  \nRahool Kumar Barman 1 , a and Sumit Biswas2 , b  \n1 Kavli IPMU (WPI), UTIAS, The University of Tokyo, Kashiwa, Chiba 277-8583, Japan  \n2 Department of Physics, Oklahoma State University, Stillwater, OK 74078, USA  \nAbstract. In this article, we review the application of modern machinelearning (ML) techniques to boost the search for processes involving the top quarks at the LHC. We revisit the formalism of Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and Attention Mechanisms. Based on recent studies, we explore their applications in designing improved top taggers, top reconstruction, and event classification tasks. We also examine the ML-based likelihood-free inference approach and generative unfolding models, focusing on their applica  \ntions to scenarios involving top quarks.  \n1 Introduction  \nThe top quark holds a unique position within and beyond the Standard Model of particle physics (SM) . Being the most massive elementary particle with an O(1) Yukawa coupling, the top quark is particularly sensitive to new physics (NP) effects, making ita strong contender to provide the initial direct clues of physics beyond the Standard Model (BSM), while also offering a rich framework to test the SM. The observational journey of the top quark started with its discovery at the Fermilab Tevatron in 1995 by the CDF and DØ collaborations [1, 2] . The CDF and DØ experiments reported 6 and 3 events, respectively, in the dileptonic channel. In the leptons+jets channel, they observed 43 and 14 events, respectively. The scenario has evolved much at the current LHC. Given the gluon-dominated parton distribution functions, the LHC has transformed into a “top factory” with roughly 80 million top quark pairs (t¯t) and an additional 34 million single top quarks produced at the integrated luminosity of L ∼ 100 fb −1 [3] . The top quark mass mt , located at the electroweak scale, mt ∼ v/ √2 , where v is the vacuum expectation value of the Higgs field, naturally connects with the electroweak symmetry breaking and the origin of the weak scale through strong dynamics [4] . Unlike others, its rapid decay, on a time scale that is significantly shorter than ΛQCD , allows one to study the intrinsic properties of a bare quark. Due to the absence of flavor-changing neutral currents at the tree level in the SM, the top quark primarily decays through weak charged currents. Its partial width can be expressed as [5],  \nΓ 􀀀t → W+ q 􀀁 ≈ 1.5 GeV ≈ 0.5~~ ~~×~~ ~~110~~ ~~−24~~ ~~s , (1)  \na  \nb  \ne-mail: [rahool.barman@ipmu.jp](rahool.barman@ipmu.jp)  \ne-mail: [sumit.biswas@okstate.edu](sumit.biswas@okstate.edu)  \n2 Will be inserted by the editor  \nwhich is larger than ΛQCD ∼ 200 MeV. This implies no observable hadronic bound states involving the top quarks, thereby enabling the tracing of the inherent properties of the top quarks from their daughter particles. Furthermore, it is the largest contributor to higher-order corrections to the Higgs mass via the top quark loops, highlighting its crucial role in BSM scenarios that aim to address the naturalness problem in the SM [6] . Recent studies have also pointed out the relevance of precise measurements of the properties of the top quarks and the Higgs boson in predicting the stability of the electroweak vacuum, which has notable cosmological implications [7] . At the LHC, the top quarks are dominantly produced in pairs, pp → t¯t, via strong interactions, with a cross-section of σt¯t = 8321929(scale)3535(PDF) pb at √s = 13 TeV, calculated at the next-to-next-to-leading order (NNLO) in QCD, including resummation of soft gluon terms at the next-to-next-to-leading logarithm (NNLL) [8, 9]. Here,(scale) and (PDF) refer to the uncertainties arising from the QCD scale and the parton distribution function (PDF), respectively. The top quarks are also produced singly in the t-cha","cbCainsQEaBi81Ks","https://ap.wps.com/l/cbCainsQEaBi81Ks","pdf",2158403,1,45,"English","en",105,"# Introduction\n## ML methods for top-quark searches\n## Applications: top tagging, reconstruction, and classification\n## Likelihood-free inference and generative unfolding\n## Context: top-quark production and physics motivation","[{\"question\":\"Why are top quarks especially important for testing new physics at the LHC?\",\"answer\":\"Top quarks are the most massive elementary particles and are highly sensitive to effects beyond the Standard Model. Their properties also provide a rich framework to test the Standard Model itself.\"},{\"question\":\"Which machine learning architectures are reviewed for improving top-quark analyses?\",\"answer\":\"The review revisits convolutional neural networks, graph neural networks, and attention mechanisms, focusing on how they can enhance top-taggers, top reconstruction, and event classification tasks.\"},{\"question\":\"What does likelihood-free inference contribute to top-quark studies?\",\"answer\":\"Likelihood-free inference supports approaches when direct likelihood evaluation is challenging, enabling improved statistical inference in top-quark scenarios. The review also discusses generative unfolding models for event-level unfolding tasks.\"}]","Top-philic Machine Learning - Review of Machine Learning Techniques for Top Quark Searches at the LHC | PDF",1785682666,113,{"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},"top-philic-machine-learning-review-of-machine-learning-techniques-for-top-quark-searches-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/top-philic-machine-learning-review-of-machine-learning-techniques-for-top-quark-searches-at-the-lhc/118256/",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","2026-08-02",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},"Why are top quarks especially important for testing new physics at the LHC?","Question",{"text":75,"@type":76},"Top quarks are the most massive elementary particles and are highly sensitive to effects beyond the Standard Model. Their properties also provide a rich framework to test the Standard Model itself.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning architectures are reviewed for improving top-quark analyses?",{"text":80,"@type":76},"The review revisits convolutional neural networks, graph neural networks, and attention mechanisms, focusing on how they can enhance top-taggers, top reconstruction, and event classification tasks.",{"name":82,"@type":73,"acceptedAnswer":83},"What does likelihood-free inference contribute to top-quark studies?",{"text":84,"@type":76},"Likelihood-free inference supports approaches when direct likelihood evaluation is challenging, enabling improved statistical inference in top-quark scenarios. The review also discusses generative unfolding models for event-level unfolding tasks.","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"]