{"id":"https://openalex.org/W7164168700","doi":"https://doi.org/10.1007/s10664-026-10891-7","title":"On the outliers of file-structure evolution: a mining study of GitHub software repositories","display_name":"On the outliers of file-structure evolution: a mining study of GitHub software repositories","publication_year":2026,"publication_date":"2026-06-11","ids":{"openalex":"https://openalex.org/W7164168700","doi":"https://doi.org/10.1007/s10664-026-10891-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-026-10891-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-026-10891-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10891-7.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10891-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138197515","display_name":"Matthijs Logemann","orcid":"https://orcid.org/0009-0001-9621-9693"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Matthijs Logemann","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138135462","display_name":"Satrio A. Rukmono","orcid":"https://orcid.org/0000-0001-9480-7216"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Satrio A. Rukmono","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029315164","display_name":"Michel R. V. Chaudron","orcid":"https://orcid.org/0000-0001-7517-6666"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Michel R. V. Chaudron","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042728295","display_name":"Jacob Kr\u00fcger","orcid":"https://orcid.org/0000-0002-0283-248X"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jacob Kr\u00fcger","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-0283-248X","affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5029315164","https://openalex.org/A5042728295","https://openalex.org/A5138135462"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75037863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9725000262260437,"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":0.9725000262260437,"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/T12127","display_name":"Software System Performance and Reliability","score":0.01119999960064888,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.0038999998942017555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6478999853134155},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6172999739646912},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.589900016784668},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4275999963283539},{"id":"https://openalex.org/keywords/software-evolution","display_name":"Software evolution","score":0.41190001368522644},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39340001344680786},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.36910000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670000195503235},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6478999853134155},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4934999942779541},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.44909998774528503},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4275999963283539},{"id":"https://openalex.org/C202105479","wikidata":"https://www.wikidata.org/wiki/Q265013","display_name":"Software evolution","level":5,"score":0.41190001368522644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3928999900817871},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39239999651908875},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C103520596","wikidata":"https://www.wikidata.org/wiki/Q7554328","display_name":"Software mining","level":5,"score":0.3637000024318695},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C171981572","wikidata":"https://www.wikidata.org/wiki/Q7554239","display_name":"Software analytics","level":5,"score":0.351500004529953},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.31529998779296875},{"id":"https://openalex.org/C198140048","wikidata":"https://www.wikidata.org/wiki/Q10859422","display_name":"Software versioning","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.2619999945163727},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2984499602","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Computer software","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10664-026-10891-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-026-10891-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10891-7.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10664-026-10891-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-026-10891-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10891-7.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164168700.pdf","grobid_xml":"https://content.openalex.org/works/W7164168700.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1491739947","https://openalex.org/W1592081868","https://openalex.org/W1966585795","https://openalex.org/W1972386298","https://openalex.org/W1973012451","https://openalex.org/W2008164297","https://openalex.org/W2025045787","https://openalex.org/W2047794235","https://openalex.org/W2055847885","https://openalex.org/W2059510240","https://openalex.org/W2076225782","https://openalex.org/W2082539579","https://openalex.org/W2097227214","https://openalex.org/W2102979206","https://openalex.org/W2121887779","https://openalex.org/W2138783984","https://openalex.org/W2139092060","https://openalex.org/W2140952846","https://openalex.org/W2146648240","https://openalex.org/W2148554434","https://openalex.org/W2151643986","https://openalex.org/W2478191067","https://openalex.org/W2503836346","https://openalex.org/W2505184898","https://openalex.org/W2715183888","https://openalex.org/W2744565623","https://openalex.org/W2780783514","https://openalex.org/W2794957215","https://openalex.org/W2888334439","https://openalex.org/W2888463767","https://openalex.org/W2889622999","https://openalex.org/W2890432166","https://openalex.org/W2899407111","https://openalex.org/W2914419291","https://openalex.org/W2991660111","https://openalex.org/W3014164501","https://openalex.org/W3020976332","https://openalex.org/W3048508766","https://openalex.org/W3090035558","https://openalex.org/W3144106047","https://openalex.org/W3163403930","https://openalex.org/W3163740924","https://openalex.org/W3176986543","https://openalex.org/W3204539481","https://openalex.org/W3208497051","https://openalex.org/W3216079787","https://openalex.org/W4200065965","https://openalex.org/W4226340964","https://openalex.org/W4229027366","https://openalex.org/W4239863959","https://openalex.org/W4245025792","https://openalex.org/W4250282767","https://openalex.org/W4255868459","https://openalex.org/W4288079288","https://openalex.org/W4288080276","https://openalex.org/W4295991108","https://openalex.org/W4380986974","https://openalex.org/W4384009620","https://openalex.org/W4386177497","https://openalex.org/W4388483628","https://openalex.org/W4389158520","https://openalex.org/W4389989068","https://openalex.org/W4395464644","https://openalex.org/W4399213295","https://openalex.org/W4400582531","https://openalex.org/W4400681542","https://openalex.org/W4401403104","https://openalex.org/W4403599799"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Context":[1],"Modern":[2],"software":[3,24,42,162,216],"systems":[4],"change":[5],"continuously.":[6],"Larger":[7],"changes":[8,40,60,104,123,135,155,221],"like":[9],"architectural":[10],"redesigns,":[11],"feature":[12],"additions,":[13],"or":[14,30,62,233],"system-wide":[15],"refactorings":[16],"regularly":[17],"impact":[18],"the":[19,85,129,159,170],"file":[20,64,132],"structures":[21,65,133],"within":[22],"a":[23,35,117,126],"repository":[25,75,254],"(i.e.,":[26,59],"developers":[27],"adding,":[28],"deleting,":[29],"moving":[31],"files).":[32],"Objective":[33],"While":[34],"normal":[36],"evolutionary":[37],"phenomenon,":[38],"file-structure":[39,92,103,154,220],"in":[41,48,74,158],"repositories":[43,108,217],"have":[44],"received":[45],"little":[46],"attention":[47],"past":[49],"research.":[50],"An":[51],"important":[52],"question":[53],"that":[54,109,153,179,209],"arises":[55],"is":[56],"whether":[57],"outliers":[58,90,180],"increasing":[61],"decreasing":[63],"more":[66,99,252],"strongly)":[67],"are":[68,156,181,196],"potential":[69,200],"signs":[70],"of":[71,91,120,131,161,166,191,199],"quality":[72,203],"issues":[73],"management":[76],"and":[77,134,143,189,202,212,230,242,248],"tooling.":[78],"Method":[79],"In":[80],"this":[81,95,139],"article,":[82],"we":[83,97,141,177],"contribute":[84],"first":[86,115],"large-scale":[87],"study":[88],"on":[89],"changes.":[93,236],"To":[94],"end,":[96],"investigated":[98],"than":[100],"12.2":[101],"million":[102],"from":[105],"94,247":[106],"GitHub":[107],"span":[110],"ten":[111],"programming":[112,185],"languages.":[113],"We":[114],"performed":[116],"quantitative":[118,150],"analysis":[119],"all":[121,167],"these":[122],"to":[124,136,244],"establish":[125],"baseline":[127],"regarding":[128],"depths":[130],"these.":[137],"Using":[138],"baseline,":[140],"identified":[142],"manually":[144],"inspected":[145],"3,049":[146],"outliers.":[147],"Results":[148],"Our":[149,206],"data":[151],"shows":[152],"pervasive":[157],"evolution":[160],"repositories,":[163],"representing":[164],"17.9%":[165],"commits":[168],"across":[169],"studied":[171],"projects.":[172],"Via":[173],"our":[174,240],"manual":[175],"inspection,":[176],"found":[178],"often":[182],"associated":[183],"with":[184],"errors,":[186],"initial":[187],"setups,":[188],"misconfigurations":[190],"package":[192],"managers.":[193],"Thus,":[194],"they":[195],"an":[197],"indicator":[198],"mistakes":[201],"problems.":[204],"Conclusions":[205],"findings":[207,243],"demonstrate":[208],"current":[210],"practices":[211],"tools":[213],"for":[214,229,251],"managing":[215],"should":[218],"take":[219],"into":[222],"account.":[223],"This":[224],"could":[225],"help":[226],"practitioners":[227],"monitor":[228],"mitigate":[231],"erroneous":[232],"unintended":[234],"structural":[235],"Researchers":[237],"can":[238],"use":[239],"methodology":[241],"design":[245],"follow-up":[246],"studies":[247],"new":[249],"techniques":[250],"robust":[253],"management.":[255]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-11T00:00:00"}