{"id":"https://openalex.org/W4416583222","doi":"https://doi.org/10.1016/j.infsof.2026.108200","title":"Mapping source code to software architecture using embedding models: Insights from an analysis of data properties","display_name":"Mapping source code to software architecture using embedding models: Insights from an analysis of data properties","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W4416583222","doi":"https://doi.org/10.1016/j.infsof.2026.108200"},"language":"en","primary_location":{"id":"doi:10.1016/j.infsof.2026.108200","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.infsof.2026.108200","pdf_url":null,"source":{"id":"https://openalex.org/S205010575","display_name":"Information and Software Technology","issn_l":"0950-5849","issn":["0950-5849","1873-6025"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information and Software Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.infsof.2026.108200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106880842","display_name":"Nils Johansson","orcid":"https://orcid.org/0000-0002-3047-4296"},"institutions":[{"id":"https://openalex.org/I1340210623","display_name":"Volvo (Sweden)","ror":"https://ror.org/05b6ypc36","country_code":"SE","type":"company","lineage":["https://openalex.org/I1340210623"]},{"id":"https://openalex.org/I223464139","display_name":"Linnaeus University","ror":"https://ror.org/00j9qag85","country_code":"SE","type":"education","lineage":["https://openalex.org/I223464139"]},{"id":"https://openalex.org/I4210157561","display_name":"V\u00e4xj\u00f6 Kommun","ror":"https://ror.org/04hwmbc03","country_code":"SE","type":"government","lineage":["https://openalex.org/I4210157561"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Nils Johansson","raw_affiliation_strings":["Linnaeus University, V\u00e4xj\u00f6, Sweden","Volvo CE, V\u00e4xj\u00f6, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-3047-4296","affiliations":[{"raw_affiliation_string":"Linnaeus University, V\u00e4xj\u00f6, Sweden","institution_ids":["https://openalex.org/I223464139"]},{"raw_affiliation_string":"Volvo CE, V\u00e4xj\u00f6, Sweden","institution_ids":["https://openalex.org/I1340210623","https://openalex.org/I4210157561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000022299","display_name":"Mauro Caporuscio","orcid":"https://orcid.org/0000-0001-6981-0966"},"institutions":[{"id":"https://openalex.org/I223464139","display_name":"Linnaeus University","ror":"https://ror.org/00j9qag85","country_code":"SE","type":"education","lineage":["https://openalex.org/I223464139"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mauro Caporuscio","raw_affiliation_strings":["Linnaeus University, V\u00e4xj\u00f6, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-6981-0966","affiliations":[{"raw_affiliation_string":"Linnaeus University, V\u00e4xj\u00f6, Sweden","institution_ids":["https://openalex.org/I223464139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106880842"],"corresponding_institution_ids":["https://openalex.org/I1340210623","https://openalex.org/I223464139","https://openalex.org/I4210157561"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00438487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"198","issue":null,"first_page":"108200","last_page":"108200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9890999794006348,"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":0.9890999794006348,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.004900000058114529,"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":0.002899999963119626,"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/code-refactoring","display_name":"Code refactoring","score":0.7591999769210815},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6680999994277954},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5730999708175659},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5080999732017517},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.47699999809265137},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.426800012588501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669000029563904},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.7591999769210815},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6680999994277954},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47679999470710754},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4052000045776367},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C35869016","wikidata":"https://www.wikidata.org/wiki/Q846636","display_name":"Software architecture","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.30730000138282776},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C174683762","wikidata":"https://www.wikidata.org/wiki/Q609588","display_name":"Component-based software engineering","level":4,"score":0.2662000060081482},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.infsof.2026.108200","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.infsof.2026.108200","pdf_url":null,"source":{"id":"https://openalex.org/S205010575","display_name":"Information and Software Technology","issn_l":"0950-5849","issn":["0950-5849","1873-6025"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information and Software Technology","raw_type":"journal-article"},{"id":"doi:10.2139/ssrn.5798927","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.5798927","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1016/j.infsof.2026.108200","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.infsof.2026.108200","pdf_url":null,"source":{"id":"https://openalex.org/S205010575","display_name":"Information and Software Technology","issn_l":"0950-5849","issn":["0950-5849","1873-6025"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information and Software Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W15334911","https://openalex.org/W2015452969","https://openalex.org/W2027147487","https://openalex.org/W2029953091","https://openalex.org/W2045257928","https://openalex.org/W2072267206","https://openalex.org/W2768908343","https://openalex.org/W2894577482","https://openalex.org/W2973136425","https://openalex.org/W3020617474","https://openalex.org/W3021175879","https://openalex.org/W3094700537","https://openalex.org/W3156333129","https://openalex.org/W3187787173","https://openalex.org/W3198694902","https://openalex.org/W3203677765","https://openalex.org/W4205524245","https://openalex.org/W4212926655","https://openalex.org/W4312061384","https://openalex.org/W4313225536","https://openalex.org/W4313343845","https://openalex.org/W4319717548","https://openalex.org/W4367844849","https://openalex.org/W4387769581","https://openalex.org/W4389980560","https://openalex.org/W4390590855","https://openalex.org/W4391114247","https://openalex.org/W4391132210","https://openalex.org/W4404697240","https://openalex.org/W4405971183","https://openalex.org/W4408248601"],"related_works":[],"abstract_inverted_index":{"Context:":[0],"Maintaining":[1],"alignment":[2],"between":[3,112],"software":[4,78],"architecture":[5],"and":[6,13,54,84,91,107,114,123,149,167,193,206],"organisational":[7],"goals":[8],"is":[9,28,35,73],"vital":[10],"for":[11,46,173],"efficiency":[12],"cost":[14],"control":[15],"during":[16],"refactoring.":[17],"Manual":[18],"reassignment":[19],"of":[20,42,109],"many":[21],"fine-grained":[22,224],"code":[23,49],"entities":[24,126],"to":[25,51,75,96],"target":[26],"modules":[27,53],"labor-intensive":[29],"when":[30,163,187],"only":[31],"heterogeneous":[32],"textual":[33,60,157],"documentation":[34,89,188],"available.":[36],"Objectives:":[37],"Provide":[38],"an":[39,43],"operational":[40],"assessment":[41],"embedding-based":[44,180,201],"approach":[45],"mapping":[47,162,181],"source":[48],"snippets":[50],"architectural":[52],"identify,":[55],"in":[56,142],"this":[57],"setting,":[58],"the":[59,143,177],"data":[61,110],"properties":[62],"that":[63],"most":[64,136,182],"clearly":[65],"condition":[66],"classification":[67,71,133],"performance.":[68],"Method:":[69],"A":[70],"pipeline":[72],"applied":[74],"six":[76],"diverse":[77],"systems.":[79],"We":[80],"classify":[81],"both":[82,210],"functions":[83],"whole":[85],"files":[86],"under":[87],"multiple":[88],"granularities":[90],"relate":[92],"macro":[93],"F1":[94],"variability":[95],"four":[97],"primary":[98],"properties:":[99],"class":[100,105,140,150,196],"separability/density,":[101],"lexical":[102,147,191],"(vocabulary)":[103],"overlap,":[104,168],"balance,":[106],"similarity":[108],"distributions":[111],"training":[113],"test":[115],"sets.":[116],"Results:":[117],"Performance":[118],"varies":[119],"markedly":[120],"across":[121],"systems":[122],"datasets;":[124],"file-level":[125,217],"generally":[127],"outperform":[128],"functions.":[129],"In":[130,176],"our":[131,213],"experiments,":[132],"gains":[134],"align":[135],"consistently":[137],"with":[138],"higher":[139],"separability/density":[141],"embedding":[144],"space,":[145],"while":[146],"overlap":[148,192,205],"balance":[151],"show":[152],"weaker,":[153],"granularity-dependent":[154],"effects.":[155],"Added":[156],"granularity":[158,218],"can":[159],"aid":[160],"function-level":[161],"it":[164],"improves":[165],"separability":[166,207],"but":[169],"may":[170],"introduce":[171],"noise":[172],"files.":[174],"Conclusions:":[175],"evaluated":[178],"pipeline,":[179],"effectively":[183],"streamlines":[184],"early":[185],"refactoring":[186],"yields":[189],"sufficient":[190],"separable,":[194],"dense":[195],"regions.":[197],"Practitioners":[198],"using":[199],"similar":[200],"approaches":[202],"should":[203],"estimate":[204],"early;":[208],"if":[209],"are":[211],"low,":[212],"results":[214],"suggest":[215],"preferring":[216],"or":[219],"enriching":[220],"descriptions":[221],"before":[222],"pursuing":[223],"(function)":[225],"mapping.":[226]},"counts_by_year":[],"updated_date":"2026-07-12T07:33:03.550515","created_date":"2025-11-25T00:00:00"}
