{"id":"https://openalex.org/W7213409333","doi":"https://doi.org/10.48550/arxiv.2609.17338","title":"Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning","display_name":"Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213409333","doi":"https://doi.org/10.48550/arxiv.2609.17338"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.17338","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17338","pdf_url":"https://arxiv.org/pdf/2609.17338","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.17338","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090520211","display_name":"Luciano Marchezan","orcid":"https://orcid.org/0000-0003-3096-580X","observed_orcids":["https://orcid.org/0000-0003-3096-580X"]},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marchezan, Luciano","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004290888","display_name":"Kevin Delcourt","orcid":"https://orcid.org/0009-0005-2988-7308","observed_orcids":["https://orcid.org/0009-0005-2988-7308"]},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Delcourt, Kevin","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049129140","display_name":"Eugene Syriani","orcid":"https://orcid.org/0000-0001-6527-1651","observed_orcids":["https://orcid.org/0000-0001-6527-1651"]},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Syriani, Eugene","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009574640","display_name":"Houari A. Sahraoui","orcid":"https://orcid.org/0000-0001-6304-9926","observed_orcids":["https://orcid.org/0000-0001-6304-9926"]},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sahraoui, Houari","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al. Montreal , QC , Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":1.0,"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":1.0,"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":0.0,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/code-clone-detection","display_name":"code clone detection","score":0.8690000176429749},{"id":"https://openalex.org/keywords/transformer-layers","display_name":"transformer layers","score":0.4830000102519989},{"id":"https://openalex.org/keywords/cross-lingual-generalization","display_name":"cross-lingual generalization","score":0.6140000224113464},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.7680000066757202},{"id":"https://openalex.org/keywords/c","display_name":"C++","score":0.9980000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722100019454956},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526000261306763},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5482000112533569},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5009999871253967},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.17338","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17338","pdf_url":"https://arxiv.org/pdf/2609.17338","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.17338","doi":"https://doi.org/10.48550/arxiv.2609.17338","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.17338","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.17338","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17338","pdf_url":"https://arxiv.org/pdf/2609.17338","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2617371268","display_name":null,"funder_award_id":"RGPIN-2025-05677","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213409333.pdf","grobid_xml":"https://content.openalex.org/works/W7213409333.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2788992245","https://openalex.org/W2942293597","https://openalex.org/W3008088841","https://openalex.org/W4286695273","https://openalex.org/W4402385880","https://openalex.org/W4416013222","https://openalex.org/W7140421492","https://openalex.org/W7196965855"],"related_works":["https://openalex.org/W4415883212","https://openalex.org/W4285238952","https://openalex.org/W7215034579","https://openalex.org/W4417510191","https://openalex.org/W2955127311","https://openalex.org/W3202575347","https://openalex.org/W4396542920","https://openalex.org/W4407433398","https://openalex.org/W4400582618","https://openalex.org/W4409295160"],"abstract_inverted_index":{"Software":[0],"clones":[1],"are":[2,7,29],"fragments":[3],"of":[4],"code":[5,112,181],"that":[6,140,169],"similar":[8],"or":[9,42,144],"functionally":[10],"equivalent":[11,31],"to":[12,100,159],"each":[13],"other.":[14],"They":[15],"pose":[16],"significant":[17],"challenges":[18],"for":[19,39,75,178],"maintenance,":[20],"refactoring,":[21],"and":[22,58,86,96,110,126,134,154,164],"bug":[23],"detection.":[24,78,183],"Detecting":[25],"Type-IV":[26,76],"clones,":[27],"which":[28,53],"semantically":[30],"but":[32],"may":[33],"differ":[34],"syntactically,":[35],"is":[36,174],"particularly":[37,162],"difficult":[38],"traditional":[40],"token-":[41],"syntax-based":[43],"methods.":[44],"Recent":[45],"machine":[46],"learning":[47,71,124,173],"approaches":[48],"rely":[49],"on":[50,80,131],"contrastive":[51,123],"learning,":[52],"requires":[54],"careful":[55],"negative":[56,148],"sampling":[57],"can":[59],"introduce":[60],"bias.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"LWVIC4Code,":[67],"a":[68,122,175],"non-contrastive":[69],"representation":[70,172],"approach":[72],"specifically":[73],"designed":[74],"clone":[77,182],"Building":[79],"the":[81],"Variance-Invariance-Covariance":[82],"Regularization":[83],"(VICReg)":[84],"framework":[85],"prior":[87],"layer-wise":[88,152,171],"VICReg":[89],"training,":[90],"LWVIC4Code":[91,120,141],"introduces":[92],"cross-layer":[93],"consistency":[94],"regularization":[95],"depth-dependent":[97],"layer":[98],"weighting":[99],"progressively":[101],"refine":[102],"semantic":[103,180],"information":[104],"across":[105],"transformer":[106],"layers,":[107],"producing":[108],"robust":[109,179],"discriminative":[111],"representations.":[113],"We":[114],"conduct":[115],"an":[116],"empirical":[117],"study":[118],"comparing":[119],"against":[121],"baseline":[125],"zero-shot":[127],"large":[128],"language":[129],"models":[130],"Python":[132,158],"(Kamino)":[133],"multi-language":[135],"(GPTCloneBench)":[136],"datasets.":[137],"Results":[138],"show":[139],"achieves":[142],"competitive":[143],"superior":[145],"performance":[146],"without":[147],"samples,":[149],"benefits":[150],"from":[151,157],"supervision,":[153],"generalizes":[155],"effectively":[156],"other":[160],"languages,":[161],"Java":[163],"C#.":[165],"These":[166],"results":[167],"demonstrate":[168],"non-contrastive,":[170],"promising":[176],"direction":[177]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-17T00:00:00"}