[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126578-en":3,"doc-seo-126578-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},126578,687207017582,"Himbo","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Novel Machine Learning and Differentiable Programming Techniques applied to the VIP-2 Underground Experiment - abstract","Work proposes machine learning and differentiable programming enhanced calibration for Silicon Drift Detectors used in the VIP-2 underground experiment at Gran Sasso. The approach reaches FWHM below 180 eV at 8 keV, improving energy resolution by about 10 eV over prior state-of-the-art. It supports in-situ correction of potential miscalibrations, reducing fine-tuning versus standard peak-finding. VIP-2 targets PEP-violating atomic transitions in copper for searches beyond the Standard Model.","arXiv :2305 . 17153v1 [physics .ins-det] 26 May 2023  \nNovel Machine Learning and Differentiable Programming Techniques applied to the VIP-2 Underground Experiment  \nFabrizio Napolitano 1 , Massimiliano Bazzi 1 , Mario Bragadireanu2,1 , Michael Cargnelli3 , Alberto Clozza 1 , Luca De Paolis 1 , Raffaele Del Grande4,1 , Carlo Fiorini5 , Carlo Guaraldo 1 , Mihail Iliescu 1 , Matthias Laubenstein6 , Simone Manti 1 , Johann Marton3 , Marco Miliucci 1,†, Kristian Piscicchia7,1 , Alessio Porcelli7,1 , Alessandro Scordo 1 , Francesco Sgaramella 1 , Diana Laura Sirghi7,1,2 , Florin Sirghi 1,2 , Oton Vazquez Doce 1 , Johann Zmeskal3,1 and Catalina Curceanu 1,2  \n1 INFN, Laboratori Nazionali di Frascati, Via E. Fermi 54, Frascati I-00044, RM, Italy  \n2 IFIN-HH, Institutul National pentru Fizica si Inginerie Nucleara Horia Hulubei, Str. Atomistilor No. 407, Bucharest-Magurele, Romania  \n3 Stefan-Meyer-Institute for Subatomic Physics, Austrian Academy of Science, Kegelgasse 27, 1030, Vienna, Austria  \n4 Physik Department E62, Technische Universit¨at M¨unchen, James-Franck-Straße 1, 85748, Garching, Germany  \n5 Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria and INFN Sezione di Milano, 20133, Milano, Italy  \n6 INFN, Laboratori Nazionali del Gran Sasso, Via G. Acitelli 22, 67100, Assergi, AQ, Italy  \n7 Centro Ricerche Enrico Fermi–Museo Storico della Fisica e Centro Studi e Ricerche  \n“Enrico Fermi”, Via Panisperna 89a, 00184, Roma, RM, Italy  \n† Current position: Italian Space Agency, Via del Politecnico, s.n.c, 00133-Roma, RM, Italy  \nE-mail: fabrizio .napolitano@lnf .infn .it  \nMay 2023  \nAbstract. In this work, we present novel Machine Learning and Differentiable Programming enhanced calibration techniques used to improve the energy resolution of the Silicon Drift Detectors (SDDs) of the VIP-2 underground experiment atthe Gran Sasso National Laboratory (LNGS) . We achieve for the first time a Full Width at Half Maximum (FWHM) in VIP-2 below 180 eV at 8 keV, improving around 10 eV on the previous state-of-the-art. SDDs energy resolution is a key parameter in the VIP-2 experiment, which is dedicated to searches for physics beyond the standard quantum theory, targeting Pauli Exclusion Principle (PEP) violating atomic transitions. Additionally, we show that this method can correct for potential miscalibrations, requiring less fine-tuning with respect to standard methods.  \n2  \nKeywords: VIP-2, SDD, Silicon Drift Detector, Differentiable Programming  \nSubmitted to: Meas. Sci. Technol.  \n1. Introduction  \nThe Pauli Exclusion Principle (PEP) is a key ingredient of the quantum theory, and its violation, albeit tiny, could be motivated by physics beyond the Standard Model, in scenarios such as the violation of Lorentz invariance, existence of extra dimensions, and quantum gravity scenarios, as discussed in recent studies [1, 2, 3] . In this context, the VIP-2 experiment [4] at the Gran Sasso National Laboratory (LNGS) searches for signals of PEP violation in the form of anomalous X-ray transitions in copper atoms, using several arrays of state-of-the-art Silicon Drift Detectors (SDDs) . The calibration of the SDDs is a critical experimental task, and it is performed in-situ using fluorescence Kα and Kβ X-rays lines from manganese and titanium, activated by a Fe-55 radioactive source, and a copper Kα line from the target material, activated by residual environmental radiation, around two orders of magnitude less intense. The PEP-violating Kα transition in copper is expected to appear just a few hundred of eV below the standard copper Kα line. In view of the experimental goal, and to ensure an accurate calibrated energy spectrum with minimal uncertainty in energy scale and resolution, precise control to determine the copper Kα transition is required. However, the difference in yield between the fluorescence lines and the copper line forces a trade-off between energy scale uncertainty and resolution. If the duration","cbCaisAuMizvfuOn","https://ap.wps.com/l/cbCaisAuMizvfuOn","pdf",784071,1,13,"English","en",105,"# Abstract\n# Introduction\n## Pauli Exclusion Principle and VIP-2 goals\n## SDD calibration with fluorescence and copper lines\n## Calibration trade-offs and limitations of standard methods\n## Neural networks and differentiable optimization","[{\"question\":\"What calibration improvement does the proposed method achieve for VIP-2 Silicon Drift Detectors?\",\"answer\":\"It achieves an energy resolution FWHM below 180 eV at 8 keV, improving by about 10 eV compared with the previous state of the art.\"},{\"question\":\"Why is the VIP-2 SDD calibration considered challenging?\",\"answer\":\"Calibration lines have different yields, creating a trade-off between uncertainty in the copper line position and the ability to track small detector response fluctuations.\"},{\"question\":\"How does differentiable programming contribute to optimizing the calibration parameters?\",\"answer\":\"The neural network outputs are refined via gradient descent in an automatic differentiation framework, where the loss is defined using an unbinned likelihood from the spectrum PDF.\"}]","Novel Machine Learning and Differentiable Programming Techniques applied to the VIP-2 Underground Experiment - abstract | PDF",1785933451,33,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"novel-machine-learning-and-differentiable-programming-techniques-applied-to-the-vip-2-underground-experiment-abstract","",{"@graph":36,"@context":86},[37,54,69],{"@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/novel-machine-learning-and-differentiable-programming-techniques-applied-to-the-vip-2-underground-experiment-abstract/126578/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What calibration improvement does the proposed method achieve for VIP-2 Silicon Drift Detectors?","Question",{"text":76,"@type":77},"It achieves an energy resolution FWHM below 180 eV at 8 keV, improving by about 10 eV compared with the previous state of the art.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Why is the VIP-2 SDD calibration considered challenging?",{"text":81,"@type":77},"Calibration lines have different yields, creating a trade-off between uncertainty in the copper line position and the ability to track small detector response fluctuations.",{"name":83,"@type":74,"acceptedAnswer":84},"How does differentiable programming contribute to optimizing the calibration parameters?",{"text":85,"@type":77},"The neural network outputs are refined via gradient descent in an automatic differentiation framework, where the loss is defined using an unbinned likelihood from the spectrum PDF.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]