{"id":"https://openalex.org/W4411450205","doi":"https://doi.org/10.1145/3729374","title":"Towards Understanding Performance Bugs in Popular Data Science Libraries","display_name":"Towards Understanding Performance Bugs in Popular Data Science Libraries","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411450205","doi":"https://doi.org/10.1145/3729374"},"language":"en","primary_location":{"id":"doi:10.1145/3729374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729374","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101818124","display_name":"H. Yang","orcid":"https://orcid.org/0009-0008-7709-2923"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowen Yang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-7709-2923","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114235334","display_name":"Zhengda Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengda Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-4679-1297","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057949305","display_name":"Zhiqing Zhong","orcid":"https://orcid.org/0000-0003-2304-9619"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqing Zhong","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2304-9619","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003326020","display_name":"Xiaoying Tang","orcid":"https://orcid.org/0000-0003-3955-1195"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoying Tang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3955-1195","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941950","display_name":"Pinjia He","orcid":"https://orcid.org/0000-0003-3377-8129"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinjia He","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3377-8129","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13708441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"FSE","first_page":"2335","last_page":"2358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.604240894317627},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5625618696212769},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.5173056125640869},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.4755280315876007},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.15504732728004456},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1501050889492035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.604240894317627},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5625618696212769},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.5173056125640869},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.4755280315876007},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.15504732728004456},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1501050889492035},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3729374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3729374","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G7609782405","display_name":null,"funder_award_id":"2024A1515010145","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2081574221","https://openalex.org/W2095839586","https://openalex.org/W2104577574","https://openalex.org/W2125341657","https://openalex.org/W2143860600","https://openalex.org/W2163661306","https://openalex.org/W2180012733","https://openalex.org/W2309295884","https://openalex.org/W2342249984","https://openalex.org/W2364861723","https://openalex.org/W2521352760","https://openalex.org/W2767209415","https://openalex.org/W2794933251","https://openalex.org/W2911282308","https://openalex.org/W2922234936","https://openalex.org/W2941232686","https://openalex.org/W2945522736","https://openalex.org/W2968594320","https://openalex.org/W2968620057","https://openalex.org/W2977058691","https://openalex.org/W2979417040","https://openalex.org/W2998795119","https://openalex.org/W3003257820","https://openalex.org/W3003877692","https://openalex.org/W3005861669","https://openalex.org/W3012094108","https://openalex.org/W3020930702","https://openalex.org/W3022760336","https://openalex.org/W3035965352","https://openalex.org/W3043199767","https://openalex.org/W3090561201","https://openalex.org/W3093621829","https://openalex.org/W3094485976","https://openalex.org/W3099878876","https://openalex.org/W3109716606","https://openalex.org/W3155949183","https://openalex.org/W3193626673","https://openalex.org/W3195794356","https://openalex.org/W3196239222","https://openalex.org/W4210788642","https://openalex.org/W4226363281","https://openalex.org/W4237993802","https://openalex.org/W4241134169","https://openalex.org/W4242145216","https://openalex.org/W4245773234","https://openalex.org/W4248878947","https://openalex.org/W4255816276","https://openalex.org/W4284677512","https://openalex.org/W4294214983","https://openalex.org/W4307926351","https://openalex.org/W4317898419","https://openalex.org/W4384009863","https://openalex.org/W4384158973","https://openalex.org/W4388961192","https://openalex.org/W4391103900","https://openalex.org/W4399795440"],"related_works":["https://openalex.org/W2030594396","https://openalex.org/W2535098331","https://openalex.org/W4280640835","https://openalex.org/W2885334669","https://openalex.org/W3215790726","https://openalex.org/W2202104725","https://openalex.org/W2354546531","https://openalex.org/W4295855176","https://openalex.org/W2068689476","https://openalex.org/W4242664608"],"abstract_inverted_index":{"With":[0],"the":[1,100,117,132,146,153,165,174,211],"increasing":[2],"demand":[3],"for":[4,66,108,167,185],"handling":[5],"large-scale":[6],"and":[7,20,33,104,140,182,189],"complex":[8],"data,":[9],"data":[10,122,127],"science":[11],"(DS)":[12],"applications":[13],"often":[14],"suffer":[15],"from":[16,92,120,197],"long":[17],"execution":[18],"time":[19],"rapid":[21],"RAM":[22],"exhaustion,":[23],"which":[24,206],"leads":[25],"to":[26,57,63,135],"many":[27],"serious":[28],"issues":[29],"like":[30],"unbearable":[31],"delays":[32],"crashes":[34],"in":[35,45,73,178],"financial":[36],"transactions.":[37],"As":[38],"popular":[39,74,94],"DS":[40,75,95,180],"libraries":[41,76,181,188],"are":[42,52],"frequently":[43],"used":[44],"these":[46,58,142],"applications,":[47],"their":[48,137],"performance":[49],"bugs":[50],"(PBs)":[51],"a":[53,86,106],"major":[54],"contributing":[55],"factor":[56],"issues,":[59],"making":[60],"it":[61],"crucial":[62],"address":[64,81],"them":[65],"improving":[67],"overall":[68],"application":[69],"performance.":[70],"However,":[71],"PBs":[72,90,103,118,154,177],"remain":[77],"largely":[78],"unexplored.":[79],"To":[80],"this":[82],"gap,":[83],"we":[84,193],"conducted":[85],"study":[87,98],"of":[88,102,116,152,176,205,214],"202":[89],"collected":[91],"seven":[93],"libraries.":[96],"Our":[97,171],"examined":[99],"impact":[101],"proposed":[105],"taxonomy":[107],"common":[109],"root":[110,138,200],"causes.":[111],"We":[112,129],"found":[113],"over":[114],"half":[115],"arise":[119],"inefficient":[121],"processing":[123],"operations,":[124],"especially":[125],"within":[126],"structure.":[128],"also":[130],"explored":[131],"effort":[133],"required":[134],"locate":[136],"causes":[139],"fix":[141],"bugs,":[143],"along":[144],"with":[145],"challenges":[147],"involved.":[148],"Notably,":[149],"around":[150],"20%":[151],"could":[155],"be":[156],"fixed":[157],"using":[158],"simple":[159],"strategies":[160],"(e.g.":[161],"Conditions":[162],"Optimizing),":[163],"suggesting":[164],"potential":[166],"automated":[168],"repair":[169],"approaches.":[170],"findings":[172],"highlight":[173],"severity":[175],"core":[179],"offer":[183],"insights":[184],"developing":[186],"high-performance":[187],"detecting":[190],"PBs.":[191],"Furthermore,":[192],"derived":[194],"test":[195],"rules":[196],"our":[198,215],"identified":[199],"causes,":[201],"identifying":[202],"eight":[203],"PBs,":[204],"four":[207],"were":[208],"confirmed,":[209],"demonstrating":[210],"practical":[212],"utility":[213],"findings.":[216]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}