{"id":"https://openalex.org/W4411962214","doi":"https://doi.org/10.3390/bdcc9070174","title":"Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories","display_name":"Boost-Classifier-Driven Fault Prediction Across Heterogeneous Open-Source Repositories","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4411962214","doi":"https://doi.org/10.3390/bdcc9070174"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9070174","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070174","pdf_url":"https://www.mdpi.com/2504-2289/9/7/174/pdf?version=1751449968","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/9/7/174/pdf?version=1751449968","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040126568","display_name":"Philip K\u00f6nig","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167190","display_name":"SBA Research","ror":"https://ror.org/05nny6x17","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210167190"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Philip K\u00f6nig","raw_affiliation_strings":["SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria"],"raw_orcid":"https://orcid.org/0009-0006-7361-6430","affiliations":[{"raw_affiliation_string":"SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria","institution_ids":["https://openalex.org/I4210167190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057376617","display_name":"Sebastian Raubitzek","orcid":"https://orcid.org/0000-0003-2206-9263"},"institutions":[{"id":"https://openalex.org/I4210167190","display_name":"SBA Research","ror":"https://ror.org/05nny6x17","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210167190"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Raubitzek","raw_affiliation_strings":["SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-2206-9263","affiliations":[{"raw_affiliation_string":"SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria","institution_ids":["https://openalex.org/I4210167190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108530040","display_name":"Alexander Schatten","orcid":"https://orcid.org/0009-0006-7645-2099"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Alexander Schatten","raw_affiliation_strings":["Institute of Information Systems Engineering, TU Wien, Favoritenstrasse 9\u201311/194, 1040 Vienna, Austria"],"raw_orcid":"https://orcid.org/0009-0006-7645-2099","affiliations":[{"raw_affiliation_string":"Institute of Information Systems Engineering, TU Wien, Favoritenstrasse 9\u201311/194, 1040 Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dennis Toth","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167190","display_name":"SBA Research","ror":"https://ror.org/05nny6x17","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210167190"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dennis Toth","raw_affiliation_strings":["SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria","institution_ids":["https://openalex.org/I4210167190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092105289","display_name":"Fabian Obermann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167190","display_name":"SBA Research","ror":"https://ror.org/05nny6x17","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210167190"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Fabian Obermann","raw_affiliation_strings":["SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria","institution_ids":["https://openalex.org/I4210167190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113778650","display_name":"Christiane K\u00f6nig","orcid":"https://orcid.org/0009-0002-1337-7504"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]},{"id":"https://openalex.org/I4210105054","display_name":"Christian Doppler Laboratory for Thermoelectricity","ror":"https://ror.org/01cbw5x35","country_code":"AT","type":"facility","lineage":["https://openalex.org/I129774422","https://openalex.org/I145847075","https://openalex.org/I4210105054"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Caroline K\u00f6nig","raw_affiliation_strings":["Christian Doppler Laboratory for Assurance and Transparency in Software Protection, Research Group Security & Privacy, Faculty of Computer Science, University of Vienna, Kolingasse 14\u201316, 1040 Vienna, Austria"],"raw_orcid":"https://orcid.org/0009-0002-1337-7504","affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Assurance and Transparency in Software Protection, Research Group Security & Privacy, Faculty of Computer Science, University of Vienna, Kolingasse 14\u201316, 1040 Vienna, Austria","institution_ids":["https://openalex.org/I4210105054","https://openalex.org/I129774422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068988506","display_name":"Kevin Mallinger","orcid":"https://orcid.org/0000-0002-3031-505X"},"institutions":[{"id":"https://openalex.org/I4210167190","display_name":"SBA Research","ror":"https://ror.org/05nny6x17","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210167190"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Kevin Mallinger","raw_affiliation_strings":["SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3031-505X","affiliations":[{"raw_affiliation_string":"SBA Research gGmbH, Floragasse 7/5.OG, 1040 Vienna, Austria","institution_ids":["https://openalex.org/I4210167190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5108530040"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":10.1073,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97837097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"9","issue":"7","first_page":"174","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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":0.9997000098228455,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9868999719619751,"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/open-source","display_name":"Open source","score":0.6448812484741211},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6209295988082886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.58607017993927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33304381370544434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32983067631721497},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32962435483932495},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16056528687477112},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.10064578056335449}],"concepts":[{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6448812484741211},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6209295988082886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.58607017993927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33304381370544434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32983067631721497},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32962435483932495},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16056528687477112},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.10064578056335449}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc9070174","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070174","pdf_url":"https://www.mdpi.com/2504-2289/9/7/174/pdf?version=1751449968","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7c2ae9f91a3d4dba96aff484f33f83e6","is_oa":true,"landing_page_url":"https://doaj.org/article/7c2ae9f91a3d4dba96aff484f33f83e6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 9, Iss 7, p 174 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc9070174","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070174","pdf_url":"https://www.mdpi.com/2504-2289/9/7/174/pdf?version=1751449968","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329167","display_name":"SBA Research","ror":"https://ror.org/05nny6x17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411962214.pdf","grobid_xml":"https://content.openalex.org/works/W4411962214.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1980851144","https://openalex.org/W2066459581","https://openalex.org/W2097883090","https://openalex.org/W2100945416","https://openalex.org/W2132887549","https://openalex.org/W2147105902","https://openalex.org/W2158744032","https://openalex.org/W2163732854","https://openalex.org/W2164519300","https://openalex.org/W2295598076","https://openalex.org/W2616916909","https://openalex.org/W2768348081","https://openalex.org/W2791527767","https://openalex.org/W2791812915","https://openalex.org/W2798476254","https://openalex.org/W2898227265","https://openalex.org/W2911964244","https://openalex.org/W2997591727","https://openalex.org/W3048348389","https://openalex.org/W3100297620","https://openalex.org/W4200452223","https://openalex.org/W4236137412","https://openalex.org/W4312106785","https://openalex.org/W4376129977","https://openalex.org/W4377027617","https://openalex.org/W4385438470","https://openalex.org/W4388427132","https://openalex.org/W4388477849","https://openalex.org/W4392611328","https://openalex.org/W4396678871","https://openalex.org/W4406729930","https://openalex.org/W4406806977","https://openalex.org/W4408324167","https://openalex.org/W6675354045","https://openalex.org/W6697187496","https://openalex.org/W6803313897"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Ensuring":[0],"reliability,":[1],"availability,":[2],"and":[3,49,57,73,85,123,139,143],"security":[4,45],"in":[5],"modern":[6],"software":[7,149],"systems":[8],"hinges":[9],"on":[10],"early":[11],"fault":[12],"detection,":[13],"yet":[14],"predicting":[15],"which":[16],"parts":[17],"of":[18,76],"a":[19,26,87,107],"codebase":[20],"are":[21,80,129],"most":[22],"at":[23],"risk":[24],"remains":[25],"significant":[27],"challenge.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,60],"analyze":[33],"2.4":[34],"million":[35],"commits":[36,94],"drawn":[37],"from":[38],"33":[39],"heterogeneous":[40],"open-source":[41],"projects,":[42],"spanning":[43],"healthcare,":[44],"tools,":[46],"data":[47],"processing,":[48],"more.":[50],"By":[51],"examining":[52],"each":[53],"repository":[54],"per":[55,58],"file":[56,66],"commit,":[59],"derive":[61],"process":[62],"metrics":[63,72],"(e.g.,":[64],"churn,":[65],"age,":[67],"revision":[68],"frequency)":[69],"alongside":[70],"size":[71],"entropy-based":[74],"indicators":[75],"how":[77],"scattered":[78,125],"changes":[79,126],"over":[81],"time.":[82],"We":[83],"train":[84],"tune":[86],"gradient":[88],"boosting":[89],"model":[90],"to":[91,132],"classify":[92],"bug-prone":[93],"under":[95],"realistic":[96],"class-imbalance":[97],"conditions,":[98],"achieving":[99],"robust":[100],"predictive":[101],"performance":[102],"across":[103],"diverse":[104],"repositories.":[105],"Moreover,":[106],"comprehensive":[108],"feature-importance":[109],"analysis":[110],"shows":[111],"that":[112],"files":[113],"with":[114],"long":[115],"lifespans":[116],"(high":[117],"age),":[118],"frequent":[119],"edits":[120],"(revision":[121],"count),":[122],"widely":[124],"(entropy":[127],"metrics)":[128],"especially":[130],"vulnerable":[131],"defects.":[133],"These":[134],"insights":[135],"can":[136],"help":[137],"practitioners":[138],"researchers":[140],"prioritize":[141],"testing":[142],"tailor":[144],"maintenance":[145],"strategies,":[146],"ultimately":[147],"strengthening":[148],"dependability.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2025-10-10T00:00:00"}
