{"id":"https://openalex.org/W4413360560","doi":"https://doi.org/10.1109/sse67621.2025.00013","title":"Unsupervised Detection of Anomalous Commits in Software Repositories","display_name":"Unsupervised Detection of Anomalous Commits in Software Repositories","publication_year":2025,"publication_date":"2025-07-07","ids":{"openalex":"https://openalex.org/W4413360560","doi":"https://doi.org/10.1109/sse67621.2025.00013"},"language":"en","primary_location":{"id":"doi:10.1109/sse67621.2025.00013","doi":"https://doi.org/10.1109/sse67621.2025.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sse67621.2025.00013","pdf_url":null,"source":{"id":"https://openalex.org/S7407086850","display_name":"IEEE International Conference on Software Services Engineering (SSE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Services Engineering (SSE)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/unsupervised-detection-of-anomalous-commits-in-software-repositories(9ff18737-8c82-4f13-b1df-d5cdc957ef75).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091112090","display_name":"Nafiseh Soveizi","orcid":"https://orcid.org/0000-0003-2111-734X","observed_orcids":["https://orcid.org/0000-0003-2111-734X"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nafiseh Soveizi","raw_affiliation_strings":["University of Amsterdam,Amsterdam,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam,Amsterdam,Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119363172","display_name":"Tom\u00e1s Candeias","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tom\u00e1s Candeias","raw_affiliation_strings":["University of Amsterdam,Amsterdam,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam,Amsterdam,Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Miroslav Zivkovic","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miroslav Zivkovic","raw_affiliation_strings":["Software Improvement Group,Amsterdam,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Improvement Group,Amsterdam,Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068341719","display_name":"Zhiming Zhao","orcid":"https://orcid.org/0000-0002-6717-9418","observed_orcids":["https://orcid.org/0000-0002-6717-9418","https://orcid.org/0000-0001-6869-430X","https://orcid.org/0000-0003-3017-7280"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhiming Zhao","raw_affiliation_strings":["University of Amsterdam,Amsterdam,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam,Amsterdam,Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9926999807357788,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9926999807357788,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.0024999999441206455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/source-code-repositories","display_name":"software repositories","score":0.8830000162124634},{"id":"https://openalex.org/keywords/unsupervised-anomaly-detection","display_name":"unsupervised anomaly detection","score":0.9660000205039978},{"id":"https://openalex.org/keywords/version-control","display_name":"version control","score":0.8130000233650208},{"id":"https://openalex.org/keywords/code-quality","display_name":"code quality","score":0.7239999771118164},{"id":"https://openalex.org/keywords/local-outlier-factor","display_name":"local outlier factor","score":0.7889999747276306},{"id":"https://openalex.org/keywords/isolation-forest","display_name":"Isolation Forest","score":1.0},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.9850000143051147},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"feature engineering","score":0.7960000038146973},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.7139999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6673365235328674},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5296950936317444},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1204281747341156}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sse67621.2025.00013","doi":"https://doi.org/10.1109/sse67621.2025.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sse67621.2025.00013","pdf_url":null,"source":{"id":"https://openalex.org/S7407086850","display_name":"IEEE International Conference on Software Services Engineering (SSE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Software Services Engineering (SSE)","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/9ff18737-8c82-4f13-b1df-d5cdc957ef75","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/unsupervised-detection-of-anomalous-commits-in-software-repositories(9ff18737-8c82-4f13-b1df-d5cdc957ef75).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/9ff18737-8c82-4f13-b1df-d5cdc957ef75","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/unsupervised-detection-of-anomalous-commits-in-software-repositories(9ff18737-8c82-4f13-b1df-d5cdc957ef75).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4733186887","display_name":null,"funder_award_id":"101129751","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G639993763","display_name":"O.S.C.A.R.S. - Open Science Clusters\u2019 Action for Research and Society","funder_award_id":"101129751","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6801968305","display_name":"ENVironmental Research Infrastructures delivering an open access Hub and NEXT-level interdisciplinary research framework providing services for advancing science and society","funder_award_id":"101131141","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G724472640","display_name":"European Virtual Institute for Research Software Excellence","funder_award_id":"101129744","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8072458336","display_name":"A federated European FAIR and Open Research Ecosystem for oceans, seas, coastal and inland waters","funder_award_id":"101094227","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320325020","display_name":"LifeWatch \u2013 Niclas \u00d6berg Foundation","ror":"https://ror.org/05f4nfp16"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1181109550","https://openalex.org/W1995443851","https://openalex.org/W2031550338","https://openalex.org/W2048696397","https://openalex.org/W2057826716","https://openalex.org/W2144182447","https://openalex.org/W2150198410","https://openalex.org/W2167778199","https://openalex.org/W2282861635","https://openalex.org/W2295124130","https://openalex.org/W2296719434","https://openalex.org/W2337344967","https://openalex.org/W2755552262","https://openalex.org/W2760451156","https://openalex.org/W2761267550","https://openalex.org/W2764012260","https://openalex.org/W2899407111","https://openalex.org/W2916268218","https://openalex.org/W2942578132","https://openalex.org/W3006537562","https://openalex.org/W3017320328","https://openalex.org/W3133567395"],"related_works":["https://openalex.org/W3133567395","https://openalex.org/W7203481087","https://openalex.org/W2755552262","https://openalex.org/W7128694049","https://openalex.org/W4400798724","https://openalex.org/W4367021049","https://openalex.org/W4402897313","https://openalex.org/W2755390068","https://openalex.org/W3207107442","https://openalex.org/W4402897293"],"abstract_inverted_index":{"Identifying":[0],"anomalous":[1,68],"commits":[2,69],"is":[3],"essential":[4],"for":[5,65],"maintaining":[6],"software":[7],"quality":[8,86],"and":[9,50,80,96,115,133,156,162,179],"reliability,":[10],"as":[11,42],"these":[12],"anomalies":[13,181],"can":[14],"indicate":[15],"potential":[16],"issues":[17],"in":[18,54,87,117,183],"code,":[19],"development":[20],"practices,":[21],"or":[22,34,74],"repository":[23],"management.":[24],"Current":[25],"anomaly":[26,118],"detection":[27,151],"methods":[28],"typically":[29],"rely":[30],"on":[31,44],"prede-fined":[32],"rules":[33],"supervised":[35],"learning,":[36],"which":[37],"suffer":[38],"from":[39],"limitations":[40],"such":[41],"dependence":[43],"labeled":[45,72],"datasets,":[46],"rigid":[47,75],"rule":[48],"definitions,":[49],"high":[51],"maintenance":[52],"overhead":[53],"rapidly":[55],"evolving":[56],"repositories.":[57,141,185],"This":[58],"paper":[59],"introduces":[60],"a":[61,78],"novel":[62],"unsupervised":[63,125],"framework":[64],"effectively":[66,153],"detecting":[67],"without":[70],"requiring":[71],"data":[73],"rules,":[76],"providing":[77,175],"scalable":[79],"adaptable":[81],"solution":[82],"to":[83],"enhance":[84],"code":[85],"modern":[88],"version":[89],"control":[90],"systems.":[91],"To":[92],"address":[93],"the":[94,149,169],"high-dimensional":[95],"mul-tifaceted":[97],"nature":[98],"of":[99,172],"commit":[100],"data,":[101],"our":[102,173],"approach":[103],"com-bines":[104],"dimensionality":[105],"reduction":[106],"techniques":[107],"with":[108],"tar-geted":[109],"feature":[110],"engineering,":[111],"enhancing":[112],"both":[113,160],"precision":[114,155],"adaptability":[116],"detection.":[119],"We":[120],"systematically":[121],"evaluate":[122],"three":[123],"state-of-the-art":[124],"techniques-Local":[126],"Outlier":[127,135],"Factor":[128],"(LOF),":[129],"Isolation":[130,146],"Forest":[131,147],"(IF),":[132],"Histogram-Based":[134],"Score":[136],"(HBOS)-across":[137],"five":[138],"diverse":[139],"open-source":[140],"Our":[142],"results":[143],"demonstrate":[144],"that":[145],"achieves":[148],"highest":[150],"accuracy,":[152],"balancing":[154],"recall":[157],"while":[158],"capturing":[159],"global":[161],"local":[163],"anomalies.":[164],"Additionally,":[165],"expert":[166],"validation":[167],"confirms":[168],"practical":[170],"relevance":[171],"approach,":[174],"insights":[176],"into":[177],"frequent":[178],"high-impact":[180],"encountered":[182],"real-world":[184]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}