{"id":"https://openalex.org/W4394745358","doi":"https://doi.org/10.1145/3597503.3639196","title":"Mining Pull Requests to Detect Process Anomalies in Open Source Software Development","display_name":"Mining Pull Requests to Detect Process Anomalies in Open Source Software Development","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394745358","doi":"https://doi.org/10.1145/3597503.3639196"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3639196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-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/A5103126336","display_name":"Bohan Liu","orcid":"https://orcid.org/0000-0002-0146-5411"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bohan Liu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420137","display_name":"He Zhang","orcid":"https://orcid.org/0000-0002-9159-5331"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Zhang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008884369","display_name":"Weigang Ma","orcid":"https://orcid.org/0009-0002-6353-2322"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigang Ma","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043601793","display_name":"Hongyu Kuang","orcid":"https://orcid.org/0009-0003-8702-2826"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Kuang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057959354","display_name":"Y. Helio Yang","orcid":"https://orcid.org/0009-0003-1081-0875"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020379523","display_name":"Jinwei Xu","orcid":"https://orcid.org/0009-0004-5157-1118"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Xu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082429541","display_name":"Shan Gao","orcid":"https://orcid.org/0009-0006-2695-2968"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Gao","raw_affiliation_strings":["Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101792932","display_name":"Jian Gao","orcid":"https://orcid.org/0009-0000-1435-8319"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Gao","raw_affiliation_strings":["Huawei, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103126336"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.1085,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81175948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9930999875068665,"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":0.7307974696159363},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.6396362781524658},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6265689730644226},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.560699462890625},{"id":"https://openalex.org/keywords/fork","display_name":"Fork (system call)","score":0.5549114346504211},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.5543118715286255},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.4851113557815552},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46597525477409363},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.4651390612125397},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.44976741075515747},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4485055208206177},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4428383708000183},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41375911235809326},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3269384503364563},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.28089410066604614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17184233665466309},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1272042691707611},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10110294818878174},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.09975185990333557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307974696159363},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6396362781524658},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6265689730644226},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.560699462890625},{"id":"https://openalex.org/C40523978","wikidata":"https://www.wikidata.org/wiki/Q14675","display_name":"Fork (system call)","level":2,"score":0.5549114346504211},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.5543118715286255},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.4851113557815552},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46597525477409363},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.4651390612125397},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.44976741075515747},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4485055208206177},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4428383708000183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41375911235809326},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3269384503364563},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.28089410066604614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17184233665466309},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1272042691707611},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10110294818878174},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.09975185990333557},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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:10.1145/3597503.3639196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.5},{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G3685832108","display_name":null,"funder_award_id":"No.62202219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3966904043","display_name":null,"funder_award_id":"No.62072227","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G480489107","display_name":null,"funder_award_id":"No.BE2021002-2","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"},{"id":"https://openalex.org/G5143702703","display_name":null,"funder_award_id":"No.72372070","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5786023838","display_name":null,"funder_award_id":"No.62302210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6375427056","display_name":null,"funder_award_id":"No.2019YFE0105500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1592081868","https://openalex.org/W1943545449","https://openalex.org/W1972452870","https://openalex.org/W1976303856","https://openalex.org/W2018449981","https://openalex.org/W2038057323","https://openalex.org/W2070603314","https://openalex.org/W2079706832","https://openalex.org/W2089838497","https://openalex.org/W2098250644","https://openalex.org/W2107564263","https://openalex.org/W2136101509","https://openalex.org/W2139092060","https://openalex.org/W2158722884","https://openalex.org/W2158891129","https://openalex.org/W2164097521","https://openalex.org/W2168248828","https://openalex.org/W2524961085","https://openalex.org/W2619400223","https://openalex.org/W2624930143","https://openalex.org/W2807825607","https://openalex.org/W2807918604","https://openalex.org/W2810649411","https://openalex.org/W2886629814","https://openalex.org/W2899099075","https://openalex.org/W2939025323","https://openalex.org/W2945190670","https://openalex.org/W2982284349","https://openalex.org/W2992895209","https://openalex.org/W3009719972","https://openalex.org/W3041596111","https://openalex.org/W3088043671","https://openalex.org/W3098078713","https://openalex.org/W3125082281","https://openalex.org/W3137814148","https://openalex.org/W3154383848","https://openalex.org/W3161438050","https://openalex.org/W4220682629","https://openalex.org/W4230949090","https://openalex.org/W4254795600","https://openalex.org/W4286331359","https://openalex.org/W4309620188","https://openalex.org/W4386171395","https://openalex.org/W4387004129"],"related_works":["https://openalex.org/W2937118960","https://openalex.org/W2808525305","https://openalex.org/W3132572030","https://openalex.org/W3208656504","https://openalex.org/W3127613622","https://openalex.org/W2808177972","https://openalex.org/W4379380002","https://openalex.org/W3085385306","https://openalex.org/W3201151259","https://openalex.org/W2483304392"],"abstract_inverted_index":{"Trustworthy":[0],"Open":[1],"Source":[2],"Software":[3],"(OSS)":[4],"development":[5,38],"processes":[6,196],"are":[7,159],"the":[8,12,21,25,28,33,50,77,81,123,131,135,144,155,164,170,191,200],"basis":[9],"that":[10,110,152],"secures":[11],"long-term":[13],"trustworthiness":[14,26],"of":[15,27,36,55,80,88,98,105,146,221],"software":[16],"projects":[17,91,128,183],"and":[18,48,52,58,68,71,75,101,119,122,142,193,206],"products.":[19],"With":[20],"aim":[22],"to":[23,46,62,73,168,227],"investigate":[24],"Pull":[29],"Request":[30],"(PR)":[31],"process,":[32,172],"common":[34],"model":[35,157,166],"collaborative":[37],"in":[39,127,154,197],"OSS":[40,90,198,228],"community,":[41,199],"we":[42,179],"exploit":[43],"process":[44],"mining":[45],"identify":[47,205],"analyze":[49,74,85,143],"normal":[51,147,214],"anomalous":[53,137,210],"patterns":[54,145],"PR":[56,148,185,195],"processes,":[57],"propose":[59],"our":[60],"approach":[61,202],"identifying":[63],"anomalies":[64,100,118],"from":[65],"both":[66,116],"control-flow":[67,99,120],"semantic":[69,106,117],"aspects,":[70],"then":[72],"synthesize":[76],"root":[78,96,103],"causes":[79,97,104,133],"identified":[82,136],"anomalies.":[83,107],"We":[84,108,139,150],"17531":[86],"PRs":[87,112,153,211],"18":[89],"on":[92],"GitHub,":[93],"extracting":[94],"26":[95],"19":[102],"find":[109,151],"most":[111],"can":[113,203],"hardly":[114],"contain":[115],"anomalies,":[121],"internal":[124],"custom":[125],"rules":[126],"may":[129],"be":[130],"key":[132],"for":[134],"PRs.":[138],"further":[140],"discover":[141],"processes.":[149],"non-fork":[156],"(42%)":[158],"far":[160],"more":[161],"likely":[162],"than":[163],"fork":[165],"(5%)":[167],"bypass":[169],"review":[171],"indicating":[173],"a":[174],"higher":[175],"potential":[176],"risk.":[177],"Besides,":[178],"analyzed":[180],"nine":[181],"poisoned":[182],"whose":[184],"practices":[186],"were":[187],"indeed":[188],"worse.":[189],"Given":[190],"complex":[192],"diverse":[194],"proposed":[201],"help":[204],"understand":[207],"not":[208],"only":[209],"but":[212],"also":[213],"PRs,":[215],"which":[216],"offers":[217],"early":[218],"risk":[219],"indications":[220],"suspicious":[222],"incidents":[223],"(such":[224],"as":[225],"poisoning)":[226],"supply":[229],"chain.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}