{"id":"https://openalex.org/W3048481822","doi":"https://doi.org/10.1007/978-3-030-99429-7_16","title":"Semantic Clone Detection via Probabilistic Software Modeling","display_name":"Semantic Clone Detection via Probabilistic Software Modeling","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3048481822","doi":"https://doi.org/10.1007/978-3-030-99429-7_16","mag":"3048481822"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-99429-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-99429-7_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-99429-7_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-99429-7_16.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044451120","display_name":"Hannes Thaller","orcid":"https://orcid.org/0000-0002-3810-0475"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Hannes Thaller","raw_affiliation_strings":["Johannes Kepler University Linz, Linz, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3810-0475","affiliations":[{"raw_affiliation_string":"Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022041640","display_name":"Lukas Linsbauer","orcid":"https://orcid.org/0000-0001-7277-5997"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Linsbauer","raw_affiliation_strings":["Technical University of Braunschweig, Braunschweig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112695865","display_name":"Alexander Egyed","orcid":null},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alexander Egyed","raw_affiliation_strings":["Johannes Kepler University Linz, Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044451120"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.8919,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82988688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"288","last_page":"309"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9961000084877014,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9922999739646912,"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/clone","display_name":"clone (Java method)","score":0.7767153978347778},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7322572469711304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7277177572250366},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.450596421957016},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44385817646980286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42275458574295044},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4147201478481293},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4078764021396637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37210941314697266},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35986050963401794},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28939288854599}],"concepts":[{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.7767153978347778},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7322572469711304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277177572250366},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.450596421957016},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44385817646980286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42275458574295044},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4147201478481293},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4078764021396637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37210941314697266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35986050963401794},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28939288854599},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-99429-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-99429-7_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-99429-7_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2008.04891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04891","pdf_url":"https://arxiv.org/pdf/2008.04891","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-99429-7_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-99429-7_16","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-99429-7_16.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048481822.pdf","grobid_xml":"https://content.openalex.org/works/W3048481822.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W121288867","https://openalex.org/W770523223","https://openalex.org/W1511986666","https://openalex.org/W1517055698","https://openalex.org/W1533109738","https://openalex.org/W1593203335","https://openalex.org/W1596790865","https://openalex.org/W1698439592","https://openalex.org/W1857184435","https://openalex.org/W2017212970","https://openalex.org/W2033398965","https://openalex.org/W2041190309","https://openalex.org/W2064035568","https://openalex.org/W2090432523","https://openalex.org/W2096491586","https://openalex.org/W2104301886","https://openalex.org/W2107592392","https://openalex.org/W2120326119","https://openalex.org/W2121077396","https://openalex.org/W2122334745","https://openalex.org/W2125260159","https://openalex.org/W2128888088","https://openalex.org/W2136099030","https://openalex.org/W2146878883","https://openalex.org/W2153887189","https://openalex.org/W2158439356","https://openalex.org/W2160455158","https://openalex.org/W2162436321","https://openalex.org/W2164030845","https://openalex.org/W2166481425","https://openalex.org/W2168891858","https://openalex.org/W2215690963","https://openalex.org/W2242464395","https://openalex.org/W2286236884","https://openalex.org/W2298313545","https://openalex.org/W2511803001","https://openalex.org/W2548028511","https://openalex.org/W2620760558","https://openalex.org/W2624703772","https://openalex.org/W2741705590","https://openalex.org/W2794744252","https://openalex.org/W2794872936","https://openalex.org/W2807866521","https://openalex.org/W2899171197","https://openalex.org/W2903211944","https://openalex.org/W2921323488","https://openalex.org/W2951409611","https://openalex.org/W2955426500","https://openalex.org/W2995317648","https://openalex.org/W2999200532","https://openalex.org/W3013624080","https://openalex.org/W3014339000","https://openalex.org/W3014453835","https://openalex.org/W3099500818","https://openalex.org/W3101433256","https://openalex.org/W3104227690","https://openalex.org/W3105535951","https://openalex.org/W3105625394","https://openalex.org/W3145100113","https://openalex.org/W3151756653","https://openalex.org/W3175483041","https://openalex.org/W4255375128","https://openalex.org/W4285719527","https://openalex.org/W4297798428","https://openalex.org/W4301168982"],"related_works":["https://openalex.org/W2377327490","https://openalex.org/W2560253012","https://openalex.org/W1524590520","https://openalex.org/W2412288087","https://openalex.org/W2371792548","https://openalex.org/W1697705604","https://openalex.org/W2419862115","https://openalex.org/W1497573972","https://openalex.org/W2071659383","https://openalex.org/W1846253165"],"abstract_inverted_index":{"Abstract":[0],"Semantic":[1,33,76],"clone":[2,34,43,62,92,214],"detection":[3,35,63,215],"is":[4,36,103,128,163],"the":[5,20,24,30,37,135,141,153],"process":[6],"of":[7,29,42,99,105,134,174,178,224],"finding":[8,120],"program":[9,101,137,179],"elements":[10,118,145,180],"with":[11,199],"similar":[12],"or":[13,193],"equal":[14,122],"runtime":[15,109],"behavior.":[16],"For":[17],"example,":[18],"detecting":[19,219],"semantic":[21,61,91,132,213],"equality":[22,127,133],"between":[23,143],"recursive":[25,220],"and":[26,87,107,115,168,185,221],"iterative":[27,222],"implementation":[28],"factorial":[31],"computation.":[32],"de":[38],"facto":[39],"technical":[40],"boundary":[41,49],"detectors.":[44],"In":[45],"recent":[46],"years,":[47],"this":[48,113,161],"has":[50],"been":[51],"tested":[52],"using":[53],"interesting":[54],"new":[55],"approaches.":[56],"This":[57,125],"article":[58],"contributes":[59],"a":[60,85,96,100,147,166,186,200],"approach":[64],"that":[65,102],"detects":[66],"clones":[67,192],"which":[68],"have":[69],"0":[70],"%":[71],"syntactic":[72],"similarity.":[73],"We":[74],"present":[75],"Clone":[77],"Detection":[78],"via":[79],"Probabilistic":[80],"Software":[81],"Modeling":[82],"(SCD-PSM)":[83],"as":[84,146,218],"stable":[86],"precise":[88],"solution":[89],"to":[90,131,158],"detection.":[93],"PSM":[94],"builds":[95],"probabilistic":[97],"model":[98,114,117,123,144],"capable":[104],"evaluating":[106],"generating":[108],"data.":[110],"SCD-PSM":[111,175,195],"leverages":[112],"its":[116],"for":[119],"behaviorally":[121],"elements.":[124,138],"behavioral":[126],"then":[129],"generalized":[130],"original":[136],"It":[139],"uses":[140],"likelihood":[142,154],"distance":[148,162],"metric.":[149],"Then,":[150],"it":[151],"employs":[152],"ratio":[155],"significance":[156],"test":[157],"decide":[159],"whether":[160,189],"significant,":[164],"given":[165],"pre-specified":[167],"controllable":[169],"false-positive":[170],"rate.":[171],"The":[172],"output":[173],"are":[176,191,209],"pairs":[177],"(i.e.,":[181],"methods),":[182],"their":[183],"distance,":[184],"decision":[187],"on":[188,211,229],"they":[190],"not.":[194],"yields":[196],"excellent":[197],"results":[198,208],"Matthews":[201],"Correlation":[202],"Coefficient":[203],"greater":[204],"than":[205],"0.9.":[206],"These":[207],"obtained":[210],"classical":[212],"problems":[216,231],"such":[217],"versions":[223],"an":[225],"algorithm,":[226],"but":[227],"also":[228],"complex":[230],"used":[232],"in":[233],"coding":[234],"competitions.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}