[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121514-en":3,"doc-seo-121514-105":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},121514,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Positive and unlabelled machine learning reveals new fast radio burst repeater candidates","Fast radio bursts (FRBs) are astronomical radio transients of unknown origin, with only a minority observed to repeat. Identifying which seemingly one-off bursts actually hide repeaters is difficult, especially because training data is positive-and-unlabelled (PU): true labels are available only for repeaters. This study applies PU-specific machine learning by training an ensemble of five PU classifiers on CHIME/FRB data to select repeater candidates. It finds 66 candidates, including 18 missed previously, and supports intrinsic physical differences between repeaters and non-repeaters.","MNRAS 00, 1–13 (2024) [https://doi.org/10.1093/mnras/stae1972](https://doi.org/10.1093/mnras/stae1972)  \nAdvance Access publication 2024 August 15  \nPositive and unlabelled machine learning reveals new fast radio burst repeater candidates  \nArjun Sharma 1‹ and Vinesh Maguire Rajpaul 2  \n1 The Shri Ram School, V-37, Moulsari Ave, Sector 24, Gurugram, Haryana 122002, India  \n2Isaac Newton Institute, University of Cambridge, 20 Clarkson Rd, Cambridge CB3 0EH, UK  \nAccepted 2024 August 10. Received 2024 August 10; in original form 2023 November 14  \nABSTRACT  \nFast radio bursts (FRBs) are astronomical radio transients of unknown origin. A minority ofFRBshave been observed to originate from repeating sources, and it is unknown which apparent one-off bursts are hidden repeaters. Recent studies increasingly suggest that there are intrinsic physical differences between repeating and non-repeating FRBs. Previous research has used machine learning classification techniques to identify apparent non-repeaters with repeater characteristics, whose sky positions would be ideal targets for future observation campaigns. However, these methods have not sufficiently accounted for the positive and unlabelled (PU) nature of the data, wherein true labels are only available for repeaters. Modified techniques that do not inadvertently learn properties of hidden repeaters as characteristic of non-repeaters are likely to identify additional repeater candidates with greater accuracy. We present in this paper the first known attempt at applying PU-specific machine learning techniques to study FRBs. We train an ensemble of five PU-specific classifiers on the available data and use them to identify 66 repeater candidates in burst data from the CHIME/FRB collaboration, 18 of which were not identified with the use of machine learning classifiers in past research. Our results additionally support repeaters and non-repeaters having intrinsically different physical properties, particularly spectral index, frequency width, and burst width. This work additionally opens new possibilities to study repeating and non-repeating FRBs using the framework of PU learning.  \nKey words: methods: data analysis–fast radio bursts.  \n1 INTRODUCTION  \nFast radio bursts (FRBs) are astronomical radio transients of unknown origin (Zhang 2023) characterized by their μs to ms-duration and high dispersion measures (Connor & Petroff 2018) . A minority of FRB sources are known to repeat. Recent literature presents two possible theories to explain this: either all FRBs repeat, with repetition intervals varying significantly across sources, or perhaps some FRBs are intrinsically one-off events, originating from a distinct sub-population compared to repeaters (Lin et al. 2023) .  \nNo progenitor model is widely agreed upon as explaining the origin of all FRBs (Platts et al. 2019; Zhang 2023), however, magnetars continue to be considered the leading model (Gordon et al. 2023; Zhang 2023; Zhang et al. 2023). Cataclysmic models have additionally been proposed as sources for one-off FRBs, with some recent results (Moroianu et al. 2023) supporting the theory that someone-off FRBs may arise from binary neutron star mergers (Falcke & Rezzolla 2014) . Another recently proposed model suggests that interactions between gravitational waves and pulsar magnetospheres may be responsible for both repeating and non-repeating FRBs (Kalita & Weltman 2023; Kushwaha, Malik & Shankaranarayanan 2024) .  \n􀀂 E-mail: [arjun.sharma07@outlook.com](arjun.sharma07@outlook.com)  \nAn increase in the number of known repeaters may significantly contribute to the development of a more complete understanding of the origin of FRBs. Since repeaters have typically been localized to host environments with greater success (Andersen et al. 2023), an increase in the understanding of FRB host galaxies caused by the identification and localization of new repeaters may contribute to abetter understanding of the physical environments which produce ","cbCaiju0VJERKkgK","https://ap.wps.com/l/cbCaiju0VJERKkgK","pdf",1197809,1,13,"English","en",105,"# Abstract\n# Introduction\n## FRB basics and repeating vs non-repeating populations\n## Physical models and proposed origins\n## Motivation for machine learning and PU learning","[{\"question\":\"What challenge does positive and unlabelled (PU) learning address in FRB studies?\",\"answer\":\"In PU learning, true labels are only available for repeaters, while other bursts are unlabeled. This makes it easy for standard classifiers to mistakenly learn hidden-repeater characteristics as if they were non-repeater traits.\"},{\"question\":\"How did the authors identify new fast radio burst repeater candidates?\",\"answer\":\"They trained an ensemble of five PU-specific classifiers on CHIME/FRB burst data and used the ensemble outputs to select candidates.\"},{\"question\":\"What evidence supports that repeaters and non-repeaters differ physically?\",\"answer\":\"The results support intrinsic differences in several burst properties, especially spectral index, frequency width, and burst width.\"}]","Positive and unlabelled machine learning reveals new fast radio burst repeater candidates | PDF",1785736041,33,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"positive-and-unlabelled-machine-learning-reveals-new-fast-radio-burst-repeater-candidates","",{"@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/positive-and-unlabelled-machine-learning-reveals-new-fast-radio-burst-repeater-candidates/121514/",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","2026-08-03",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},"What challenge does positive and unlabelled (PU) learning address in FRB studies?","Question",{"text":75,"@type":76},"In PU learning, true labels are only available for repeaters, while other bursts are unlabeled. This makes it easy for standard classifiers to mistakenly learn hidden-repeater characteristics as if they were non-repeater traits.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How did the authors identify new fast radio burst repeater candidates?",{"text":80,"@type":76},"They trained an ensemble of five PU-specific classifiers on CHIME/FRB burst data and used the ensemble outputs to select candidates.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence supports that repeaters and non-repeaters differ physically?",{"text":84,"@type":76},"The results support intrinsic differences in several burst properties, especially spectral index, frequency width, and burst width.","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"]