[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127346-en":3,"doc-seo-127346-105":31,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127346,962085564381,"Clementine","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Advancing glitch classification in Gravity Spy - multi-view fusion with attention-based machine learning for Advanced LIGO’s fourth observing run","Ground-based observatories such as LIGO detect gravitational waves together with disruptive non-Gaussian noise artifacts called glitches that can confuse or mask real signals. The Gravity Spy community-science project combines human insight with machine learning to classify glitches, but its integrated model has faced limitations during Advanced LIGO’s O4 run because of architectural simplicity and inadequate generalization for multi-time-window inputs. This work develops an enhanced O4 glitch classifier using prior-run data, comparing fusion strategies for multi-time inputs, applying label smoothing to mitigate noisy labels, and adding attention-based modules for improved interpretability.","Classical and Quantum   \n Gravity   \nPAPER • OPEN ACCESS  \nAdvancing glitch classification in Gravity Spy: multi-view fusion with attention-based machine learning for Advanced LIGO’s fourth observing run  \nTo cite this article: Yunan Wu et al 2025 Class. Quantum Grav. 42 165015  \nYou may also like  \n-Utilizing aLIGO glitch classifications to validate gravitational-wave candidates  \nDerek Davis, Laurel V White and Peter RSaulson  \n-Data quality up to the third observing run of advanced LIGO: Gravity Spy glitch classifications  \nJ Glanzer, S Banagiri, S B Coughlin et al.  \n-GSpyNetTree: a signal-vs-glitch classifier for gravitational-wave event candidates  \nSofía Álvarez-López, Annudesh Liyanage, Julian Ding et al.  \nView the article online for updates and enhancements.  \nThis content was downloaded from IP address [130.209.157.53](130.209.157.53) on 01/10/2025 at 14:42  \nClass. Quantum Grav. 42 (2025) 165015 (24pp) [https://doi.org/10.1088/1361-6382/adf58b](https://doi.org/10.1088/1361-6382/adf58b)  \nAdvancing glitch classification in Gravity Spy: multi-view fusion with attention-based machine learning for Advanced LIGO’s fourth observing run  \nYunan Wu 1 􀁂, Michael Zevin2,3 􀁂, Christopher P L Berry4, ∗ 􀁂 , Kevin Crowston5 􀁂, Carsten Østerlund5 􀁂 ,  \nZoheyr Doctor3,6 􀁂, Sharan Banagiri3 􀁂, Corey B Jackson7 􀁂 , Vicky Kalogera3,6 􀁂 and Aggelos K Katsaggelos 1,3 􀁂  \n1 The Department of Electrical Computer Engineering, Northwestern University, 2145 Sheridan Road, Evanston 60208, IL, United States of America  \n2 The Adler Planetarium, 1300 South DuSable Lake Shore Drive, Chicago 60605, IL, United States of America  \n3 Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA), Northwestern University, 1800 Sherman Ave, Evanston 60201, IL, United States of America  \n4 SUPA, School of Physics and Astronomy, University of Glasgow, Kelvin Building, University Ave, Glasgow 8QQ, G12, United Kingdom  \n5 School of Information Studies, Syracuse University, 343 Hinds Hall, Syracuse 13210, NY, United States of America  \n6 Department of Physics and Astronomy, Northwestern University, 2145 Sheridan Road, Evanston 60208, IL, United States of America  \n7 Information School, University of Wisconsin–Madison, 600 N Park Street, Madison 53706, WI, United States of America  \nE-mail: [christopher.berry.2@glasgow.ac.uk](christopher.berry.2@glasgow.ac.uk)  \nReceived 28 January 2025; revised 10 July 2025 Accepted for publication 29 July 2025  \nPublished 14 August 2025  \nAbstract  \nThe first successful detection of gravitational waves by ground-based observatories, such as the Laser Interferometer Gravitational-Wave Observatory (LIGO), marked a breakthrough in our comprehension of the Universe.  \n∗  \nAuthor to whom any correspondence should be addressed.  \nOriginal Content from this work may be used under the terms of the Creative Commons Attribution  \n4.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.  \n© 2025 The Author(s) . Published by IOP Publishing Ltd 1  \nHowever, due to the unprecedented sensitivity required to make such observations, gravitational-wave detectors also capture disruptive noise sources called glitches, which can potentially be confused for or mask gravitationalwave signals. To address this problem, a community-science project, Gravity Spy, incorporates human insight and machine learning to classify glitches in LIGO data. The machine-learning classifier, integrated into the project since 2017, has evolved over time to accommodate increasing numbers of glitch classes. Despite its success, limitations have arisen in the ongoing LIGO fourth observing run (O4) due to the architecture’s simplicity, which led to poor generalization and inability to handle multi-time window inputs effectively. We propose an advanced classifier for O4 glitches. Using data from previous observing runs, we evaluate different fusion strategies for mu","cbCaiqDLSNIjG30i","https://ap.wps.com/l/cbCaiqDLSNIjG30i","pdf",5304026,2,1,25,"English","en",105,"# Introduction\n## Background and motivation\n## Glitches and their impact on detections\n## Gravity Spy and its evolving classifier","[{\"question\":\"Why is glitch classification important for gravitational-wave detection in LIGO data?\",\"answer\":\"Glitches are non-Gaussian noise transients that can obscure or be mistaken for true gravitational-wave signals. Classifying them improves detector data quality and analysis reliability.\"},{\"question\":\"What limitations arise in Gravity Spy’s classifier during Advanced LIGO’s fourth observing run (O4)?\",\"answer\":\"The paper reports that architectural simplicity led to poor generalization and difficulties handling multi-time-window inputs effectively during O4.\"},{\"question\":\"How does the proposed method improve O4 glitch classification?\",\"answer\":\"It evaluates fusion strategies for multi-time-window inputs using previous observing-run data, applies label smoothing to counter noisy labels, and uses attention-module-generated weights to improve interpretability.\"}]","Advancing glitch classification in Gravity Spy - multi-view fusion with attention-based machine learning for Advanced LIGO’s fourth observing run | PDF",1785938409,63,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"advancing-glitch-classification-in-gravity-spy-multi-view-fusion-with-attention-based-machine-learning-for-advanced-ligos-fourth-observing-run-127346","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/advancing-glitch-classification-in-gravity-spy-multi-view-fusion-with-attention-based-machine-learning-for-advanced-ligos-fourth-observing-run-127346/127346/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"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},"Why is glitch classification important for gravitational-wave detection in LIGO data?","Question",{"text":76,"@type":77},"Glitches are non-Gaussian noise transients that can obscure or be mistaken for true gravitational-wave signals. Classifying them improves detector data quality and analysis reliability.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What limitations arise in Gravity Spy’s classifier during Advanced LIGO’s fourth observing run (O4)?",{"text":81,"@type":77},"The paper reports that architectural simplicity led to poor generalization and difficulties handling multi-time-window inputs effectively during O4.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed method improve O4 glitch classification?",{"text":85,"@type":77},"It evaluates fusion strategies for multi-time-window inputs using previous observing-run data, applies label smoothing to counter noisy labels, and uses attention-module-generated weights to improve interpretability.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]