[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121102-en":3,"doc-seo-121102-105":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":20,"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},121102,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Explainable Machine Learning Identification of Superconductivity from Single-Particle Spectral Functions","Traditional identification of symmetry-breaking phase transitions via emergence of a single-particle gap faces major difficulties in quantum materials with strong fluctuations. A domain-adversarial neural network is developed using simulated cuprate spectra to create a data-driven solution that mitigates limited experimental datasets by exploiting abundant theoretical spectra. Applied to unlabeled experimental spectra, the model separates true superconductivity from gapped fluctuating states without intensive temperature sampling. Model explanations highlight that Fermi-surface spectral intensity remains crucial even within gapped states.","arXiv :2406 .04445v1 [ cond-mat .supr-con] 6 Jun 2024  \nExplainable Machine Learning Identification of Superconductivity from  \nSingle-Particle Spectral Functions  \nXu Chen, 1, ∗ Yuanjie Sun,2, ∗ Eugen Hruska, 1 Vivek Dixit,2 Jinming Yang,3 Yu He,4,† Yao Wang, 1, 2,‡ and Fang Liu 1, §  \n1 Department of Chemistry, Emory University, Atlanta, GA 30322, United States  \n2 Department of Physics and Astronomy, Clemson University, Clemson, SC 29631, United States  \n3 Department of Physics, Yale University, New Haven CT, 06511, United States  \n4 Department of Applied Physics, Yale University, New Haven CT, 06511, United States (Dated: June 10, 2024)  \nAbstract: The traditional method of identifying symmetry-breaking phase transitions through the emergence of a single-particle gap encounters significant challenges in quantum materials with strong fluctuations. To address this, we have developed a data-driven approach using a domainadversarial neural network trained on simulated spectra of cuprates. This model compensates for the scarcity of experimental data – a significant barrier to the wide deployment of machine learning in physical research – by leveraging the abundance of theoretically simulated data. When applied to unlabeled experimental spectra, our model successfully distinguishes the true superconducting states from gapped fluctuating states, without the need for fine temperature sampling across the transition. Further, the explanation of our machine learning model reveals the crucial role of the Fermi-surface spectral intensity even in gapped states. It paves the way for robust and direct spectroscopic identification of fluctuating orders, particularly in low-dimensional, strongly correlated materials.  \nUnderstanding and controlling the materials’ physical properties are key pursuits of the quantum materials research today. Since the electronic structure of materials underpins many physical properties, the single-particle spectral function proves to be an effective quantity for their characterization[1] . This function captures the probability of an individual electron occupying a specific energy-momentum state in a many-electron system. While it cannot replace the full many-body wavefunction, it provides insights into the low-energy properties such as conductivity and thermal excitations. Notably, the single-particle spectral function can be directly measured using angle-resolved photoemission spectroscopy (ARPES) . Both lab-based and synchrotronbased ARPES techniques have been extensively employed to investigate emergent electronic states in materials[2, 3], substantially accelerating the advancement in the field of quantum materials[4] .  \nAs investigations into quantum materials deepen, new challenges arise due to the inherent limitations of representing a many-body state with only its single-particle excitations. For traditional metals and semiconductors, this approximation is effective as interactions are sufficiently screened. In such scenarios, ARPES can accurately identify electronic phase transitions through a single-particle gap, stemming from the development of a (mean-field) order parameter. By measuring the energy gap size, one can deduce the strength of order parameters. However, in quantum materials, emergent phases are substantially influenced, or even governed, by entanglement among multiple particles. Consequently,  \n∗ X.C. and Y.S. contributed equally to this work.  \n†  \n‡  \n§  \n[yu.he@yale.edu](yu.he@yale.edu)[ ](yu.he@yale.edu)[yao.wang@emory.edu](yao.wang@emory.edu)[ ](yao.wang@emory.edu)[fang.liu@emory.edu](fang.liu@emory.edu)  \nFIG. 1. Schematic illustrating the single-particle gap in materials experiencing strong fluctuations. At low temperatures (red), the material exhibits a nonzero order parameter ⟨∆⟩  0 and a well-defined single-particle gap. As the temperature increases above Tc (green), the local excitations lose long-range coherence and the average order parameter ⟨∆⟩ = 0 . However, the syste","cbCaitpn2f3AFZsp","https://ap.wps.com/l/cbCaitpn2f3AFZsp","pdf",2991720,1,"English","en",105,"# Abstract\n## Motivation: limits of single-particle gap in fluctuating quantum materials\n## Data-driven approach: domain-adversarial neural network from simulated spectra\n## Results: distinguishing superconducting vs fluctuating gapped states\n## Interpretability: role of Fermi-surface spectral intensity\n## Background: spectral functions and ARPES measurements","[{\"question\":\"Why is identifying superconducting phase transitions difficult using a single-particle gap?\",\"answer\":\"In strongly fluctuating quantum materials, short-range fluctuations can cause partial spectral-weight depletion that mimics gap-like behavior, even when long-range order has not fully formed.\"},{\"question\":\"How does the proposed method address the scarcity of experimental spectra?\",\"answer\":\"It trains a domain-adversarial neural network on simulated cuprate spectra, using theoretically generated data to compensate for limited experimental training samples.\"},{\"question\":\"What does the model achieve when applied to unlabeled experimental spectra?\",\"answer\":\"It distinguishes true superconducting states from gapped fluctuating states without requiring fine temperature sampling across the transition.\"}]","Explainable Machine Learning Identification of Superconductivity from Single-Particle Spectral Functions | PDF",1785733735,20,{"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},"explainable-machine-learning-identification-of-superconductivity-from-single-particle-spectral-functions","",{"@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/explainable-machine-learning-identification-of-superconductivity-from-single-particle-spectral-functions/121102/",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","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is identifying superconducting phase transitions difficult using a single-particle gap?","Question",{"text":74,"@type":75},"In strongly fluctuating quantum materials, short-range fluctuations can cause partial spectral-weight depletion that mimics gap-like behavior, even when long-range order has not fully formed.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed method address the scarcity of experimental spectra?",{"text":79,"@type":75},"It trains a domain-adversarial neural network on simulated cuprate spectra, using theoretically generated data to compensate for limited experimental training samples.",{"name":81,"@type":72,"acceptedAnswer":82},"What does the model achieve when applied to unlabeled experimental spectra?",{"text":83,"@type":75},"It distinguishes true superconducting states from gapped fluctuating states without requiring fine temperature sampling across the transition.","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"]