{"id":"https://openalex.org/W7125908341","doi":"https://doi.org/10.1109/ase63991.2025.00112","title":"Detecting Semantic Clones of Unseen Functionality","display_name":"Detecting Semantic Clones of Unseen Functionality","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7125908341","doi":"https://doi.org/10.1109/ase63991.2025.00112"},"language":"en","primary_location":{"id":"doi:10.1109/ase63991.2025.00112","doi":"https://doi.org/10.1109/ase63991.2025.00112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00112","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"IEEE/ACM International Conference on Automated Software Engineering (ASE)","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 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.04143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124112651","display_name":"Konstantinos Kitsios","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Konstantinos Kitsios","raw_affiliation_strings":["University of Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056310041","display_name":"Francesco Sovrano","orcid":"https://orcid.org/0000-0002-6285-1041","observed_orcids":["https://orcid.org/0000-0002-6285-1041"]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Francesco Sovrano","raw_affiliation_strings":["University of Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076587279","display_name":"Earl T. Barr","orcid":"https://orcid.org/0000-0003-0771-7891","observed_orcids":["https://orcid.org/0000-0003-0771-7891"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Earl T. Barr","raw_affiliation_strings":["University College London,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London,London,UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082720005","display_name":"Alberto Bacchelli","orcid":"https://orcid.org/0000-0003-0193-6823","observed_orcids":["https://orcid.org/0000-0003-0193-6823"]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alberto Bacchelli","raw_affiliation_strings":["University of Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1261,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88541336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1312","last_page":"1324"},"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9610000252723694},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8130000233650208},{"id":"https://openalex.org/keywords/code-similarity","display_name":"code similarity","score":0.5},{"id":"https://openalex.org/keywords/generalization-to-unseen-classes","display_name":"generalization to unseen classes","score":0.5109999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304999828338623},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6761999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6671000123023987},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6259999871253967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4991999864578247},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.4577000141143799},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4438999891281128},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ase63991.2025.00112","doi":"https://doi.org/10.1109/ase63991.2025.00112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00112","pdf_url":null,"source":{"id":"https://openalex.org/S4363608212","display_name":"IEEE/ACM International Conference on Automated Software Engineering (ASE)","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 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.04143","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.04143","pdf_url":"https://arxiv.org/pdf/2510.04143","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.04143","doi":"https://doi.org/10.48550/arxiv.2510.04143","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.04143","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5167/uzh-435833","doi":"https://doi.org/10.5167/uzh-435833","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-435833","pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"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":"ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.04143","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.04143","pdf_url":"https://arxiv.org/pdf/2510.04143","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/G2663829463","display_name":"Enhanced Code Review: Using Context and Learning from Review Experience","funder_award_id":"197227","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G993971353","display_name":null,"funder_award_id":"200021","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7125908341.pdf","grobid_xml":"https://content.openalex.org/works/W7125908341.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1565746575","https://openalex.org/W1614298861","https://openalex.org/W1698439592","https://openalex.org/W1973650376","https://openalex.org/W1994243621","https://openalex.org/W2041190309","https://openalex.org/W2047764386","https://openalex.org/W2065053490","https://openalex.org/W2065622239","https://openalex.org/W2066455950","https://openalex.org/W2090432523","https://openalex.org/W2109943392","https://openalex.org/W2115534035","https://openalex.org/W2119887272","https://openalex.org/W2143960295","https://openalex.org/W2144886241","https://openalex.org/W2157532207","https://openalex.org/W2158439356","https://openalex.org/W2171293873","https://openalex.org/W2282866165","https://openalex.org/W2490662969","https://openalex.org/W2508865106","https://openalex.org/W2578208870","https://openalex.org/W2626778328","https://openalex.org/W2726916722","https://openalex.org/W2741705590","https://openalex.org/W2767717989","https://openalex.org/W2891332953","https://openalex.org/W2954552517","https://openalex.org/W2955426500","https://openalex.org/W2972009176","https://openalex.org/W2972818416","https://openalex.org/W3005276469","https://openalex.org/W3008088841","https://openalex.org/W3013132080","https://openalex.org/W3014339000","https://openalex.org/W3018033251","https://openalex.org/W3037950768","https://openalex.org/W3040955294","https://openalex.org/W3043078865","https://openalex.org/W3086007799","https://openalex.org/W3098605233","https://openalex.org/W3107551709","https://openalex.org/W3126675481","https://openalex.org/W3135147155","https://openalex.org/W4210550462","https://openalex.org/W4235786747","https://openalex.org/W4239510810","https://openalex.org/W4252684946","https://openalex.org/W4285238952","https://openalex.org/W4312465319","https://openalex.org/W4312691425","https://openalex.org/W4312803897","https://openalex.org/W4313483544","https://openalex.org/W4384155305","https://openalex.org/W4384302803","https://openalex.org/W4385380915","https://openalex.org/W4386142439","https://openalex.org/W4386472818","https://openalex.org/W4389158355","https://openalex.org/W4389544307","https://openalex.org/W4393034946","https://openalex.org/W4393284202","https://openalex.org/W4394745980","https://openalex.org/W4398766423","https://openalex.org/W4400277330","https://openalex.org/W4400681662","https://openalex.org/W4403255280","https://openalex.org/W4404131920","https://openalex.org/W4404782964","https://openalex.org/W4407423361","https://openalex.org/W4416013222"],"related_works":["https://openalex.org/W4210550462","https://openalex.org/W4285238952","https://openalex.org/W4403255280","https://openalex.org/W6981905498","https://openalex.org/W4405602123","https://openalex.org/W7204182557","https://openalex.org/W4319451764","https://openalex.org/W2910039116","https://openalex.org/W4417098770","https://openalex.org/W4402896859"],"abstract_inverted_index":{"Semantic":[0],"code":[1,13],"clone":[2,87,165],"detection":[3,88],"is":[4,95,275],"the":[5,15,92,130,185,192,206,235,239,248,257,262],"task":[6,131],"of":[7,12,68,74,99,109,114,132,135,145,187,194,199,238,272],"detecting":[8,133],"whether":[9],"two":[10,222],"snippets":[11],"implement":[14],"same":[16],"functionality":[17,101,274],"(e.g.,":[18],"Sort":[19],"Array).":[20],"Recently,":[21],"many":[22],"neural":[23],"models":[24,32,125,160,196,241,285],"achieved":[25],"near-perfect":[26],"performance":[27,193],"on":[28,38,107,129,156,197,261,270],"this":[29,78,115],"task.":[30],"These":[31],"seek":[33],"to":[34,48,58,96,147,170,177,190,259,279,288],"make":[35],"inferences":[36],"based":[37],"their":[39],"training":[40,54,163],"data.":[41],"Consequently,":[42],"they":[43,50,61,226],"better":[44,169],"detect":[45,59,97],"clones":[46,66,98,108,134,198,265,271],"similar":[47],"those":[49,60],"have":[51,62],"seen":[52],"during":[53,231],"and":[55,126,183,209,266,286,294],"may":[56],"struggle":[57],"not.":[63],"Developers":[64],"seeking":[65],"are,":[67],"course,":[69],"interested":[70],"in":[71,90,143],"both":[72,123],"types":[73],"clones.":[75],"We":[76,202,233],"confirm":[77],"claim":[79],"through":[80],"a":[81,100,141,243],"literature":[82],"review,":[83],"identifying":[84],"three":[85],"practical":[86],"tasks":[89],"which":[91],"model\u2019s":[93],"goal":[94],"even":[102,224],"if":[103,225],"it":[104],"was":[105],"trained":[106],"different":[110],"functionalities.":[111],"In":[112],"light":[113],"finding,":[116],"we":[117,251],"re-evaluate":[118],"six":[119],"state-of-the-art":[120],"models,":[121],"including":[122],"task-specific":[124,152,159,240,284],"generative":[127,249],"LLMs,":[128],"unseen":[136,171,200,230,273],"functionality.":[137,201],"Our":[138],"experiments":[139],"reveal":[140],"drop":[142],"F1":[144,174,269],"up":[146,176,278,287],"48%":[148],"(average":[149,179,281,290],"31%)":[150],"for":[151,164,247,283,292],"models.":[153],"LLMs":[154,250,258],"perform":[155],"par":[157],"with":[158,242],"without":[161],"explicit":[162],"detection,":[166],"but":[167],"generalize":[168],"functionalities,":[172],"where":[173,214],"drops":[175],"5%":[178,289],"3%)":[180,291],"instead.We":[181],"propose":[182,252],"evaluate":[184],"use":[186],"contrastive":[188,215,244,253],"learning":[189,216],"improve":[191],"existing":[195],"draw":[203],"inspiration":[204],"from":[205,228],"computer":[207],"vision":[208],"natural":[210],"language":[211],"processing":[212],"fields":[213],"excels":[217],"at":[218],"measuring":[219],"similarity":[220],"between":[221,264],"objects,":[223],"come":[227],"classes":[229],"training.":[232],"replace":[234],"final":[236],"classifier":[237],"classifier,":[245],"while":[246],"in-context":[254],"learning,":[255],"guiding":[256],"focus":[260],"differences":[263],"non-clones.":[267],"The":[268],"improved":[276],"by":[277],"26%":[280],"9%)":[282],"LLMs.Data":[293],"material:":[295],"https://doi.org/10.5281/zenodo.17238379":[296]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-01-29T00:00:00"}