{"id":"https://openalex.org/W7141484058","doi":"https://doi.org/10.1007/s10009-026-00842-4","title":"Understanding code semantics: a benchmark study of LLMs","display_name":"Understanding code semantics: a benchmark study of LLMs","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7141484058","doi":"https://doi.org/10.1007/s10009-026-00842-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10009-026-00842-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10009-026-00842-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10009-026-00842-4.pdf","source":{"id":"https://openalex.org/S122567160","display_name":"International Journal on Software Tools for Technology Transfer","issn_l":"1433-2779","issn":["1433-2779","1433-2787"],"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":"International Journal on Software Tools for Technology Transfer","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/s10009-026-00842-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010877867","display_name":"Cosimo Laneve","orcid":"https://orcid.org/0000-0002-0052-4061"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Cosimo Laneve","raw_affiliation_strings":["DISI, University of Bologna, Bologna, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DISI, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075714363","display_name":"Alvise Span\u00f2","orcid":"https://orcid.org/0000-0002-6905-2736"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alvise Span\u00f2","raw_affiliation_strings":["DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017911259","display_name":"Dalila Ressi","orcid":"https://orcid.org/0000-0001-5291-5438"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Dalila Ressi","raw_affiliation_strings":["DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015760641","display_name":"Sabina Rossi","orcid":"https://orcid.org/0000-0002-1189-4439"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabina Rossi","raw_affiliation_strings":["DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077037306","display_name":"Michele Bugliesi","orcid":"https://orcid.org/0000-0002-4567-3351"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Bugliesi","raw_affiliation_strings":["DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAIS, Ca\u2019 Foscari University of Venice, Venezia Mestre, Italy","institution_ids":["https://openalex.org/I149461666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010877867"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":48.6846,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.996751,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"28","issue":"3","first_page":"329","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.6699000000953674,"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":0.6699000000953674,"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":0.06159999966621399,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.7175999879837036},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6941999793052673},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5547999739646912},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.5507000088691711},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.512499988079071},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886000275611877},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7175999879837036},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6941999793052673},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5547999739646912},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5162000060081482},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366999924182892},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.26930001378059387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10009-026-00842-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10009-026-00842-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10009-026-00842-4.pdf","source":{"id":"https://openalex.org/S122567160","display_name":"International Journal on Software Tools for Technology Transfer","issn_l":"1433-2779","issn":["1433-2779","1433-2787"],"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":"International Journal on Software Tools for Technology Transfer","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10009-026-00842-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10009-026-00842-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10009-026-00842-4.pdf","source":{"id":"https://openalex.org/S122567160","display_name":"International Journal on Software Tools for Technology Transfer","issn_l":"1433-2779","issn":["1433-2779","1433-2787"],"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":"International Journal on Software Tools for Technology Transfer","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7578878998756409,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1511544777","display_name":null,"funder_award_id":"E53C23001670001","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3752830834","display_name":null,"funder_award_id":"CUP E53C23001670001","funder_id":"https://openalex.org/F4320311030","funder_display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\""},{"id":"https://openalex.org/G4772130973","display_name":null,"funder_award_id":"E53C23001670001","funder_id":"https://openalex.org/F4320334079","funder_display_name":"Gruppo Nazionale per il Calcolo Scientifico"},{"id":"https://openalex.org/G4917700297","display_name":null,"funder_award_id":"PE0000014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4945003250","display_name":null,"funder_award_id":"CUP E53C23001670001","funder_id":"https://openalex.org/F4320334079","funder_display_name":"Gruppo Nazionale per il Calcolo Scientifico"},{"id":"https://openalex.org/G5488169599","display_name":null,"funder_award_id":"E53C23001670001","funder_id":"https://openalex.org/F4320311030","funder_display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\""}],"funders":[{"id":"https://openalex.org/F4320311030","display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\"","ror":"https://ror.org/01vx64p53"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334079","display_name":"Gruppo Nazionale per il Calcolo Scientifico","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7141484058.pdf","grobid_xml":"https://content.openalex.org/works/W7141484058.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2947017203","https://openalex.org/W3004658838","https://openalex.org/W3021792233","https://openalex.org/W3114632476","https://openalex.org/W3131641316","https://openalex.org/W3167948855","https://openalex.org/W4309773749","https://openalex.org/W4367672983","https://openalex.org/W4382246098","https://openalex.org/W4391184004","https://openalex.org/W4391559941","https://openalex.org/W4392388527","https://openalex.org/W4399120662","https://openalex.org/W4402696041","https://openalex.org/W4410552841","https://openalex.org/W7124740847"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"We":[1,132],"present":[2],"an":[3],"empirical":[4],"study":[5],"on":[6,143,150],"the":[7,29,33,44,97,126,130],"ability":[8],"of":[9,61,108,129],"Large":[10],"Language":[11],"Models":[12],"(LLMs)":[13],"to":[14],"understand":[15],"code":[16,50,94,175],"by":[17,47,166],"detecting":[18],"semantically":[19],"equivalent":[20,67,109,144],"and":[21,55,68,80,86,113,145],"inequivalent":[22],"programs,":[23],"that":[24,134,178],"is,":[25],"whether":[26],"they":[27],"compute":[28],"same":[30,34],"result":[31],"given":[32],"input":[35],"or":[36,148,173],"not.":[37],"To":[38],"probe":[39],"this,":[40],"we":[41,71],"deliberately":[42],"perturb":[43],"program":[45],"text":[46],"introducing":[48],"semantics-preserving":[49],"transformations,":[51],"namely":[52],"copy":[53],"propagation":[54],"constant":[56],"folding.":[57],"Using":[58],"a":[59],"benchmark":[60],"11":[62],"Python":[63],"functions":[64],"with":[65,85,115,176],"both":[66],"non-equivalent":[69],"variants,":[70],"evaluate":[72],"seven":[73],"state-of-the-art":[74],"LLMs":[75,136],"(including":[76],"ChatGPT,":[77],"Claude,":[78],"Gemini,":[79],"Deep-Seek)":[81],"under":[82],"zero-shot":[83],"prompting,":[84],"without":[87,111],"minimal":[88],"context.":[89,116],"Despite":[90],"strong":[91],"performance":[92],"in":[93,101],"generation":[95],"tasks,":[96],"models":[98],"often":[99],"fail":[100],"this":[102],"deeper":[103],"reasoning":[104],"challenge,":[105],"misclassifying":[106],"41%":[107],"cases":[110],"context":[112],"29%":[114],"Although":[117],"prompting":[118],"can":[119,162],"improve":[120],"performance,":[121],"it":[122],"does":[123],"not":[124],"address":[125],"underlying":[127],"limitations":[128],"models.":[131],"argue":[133],"improving":[135],"themselves,":[137],"through":[138],"targeted":[139],"fine-tuning,":[140],"contrastive":[141],"learning":[142],"nonequivalent":[146],"implementations,":[147],"training":[149],"transformation-invariant":[151],"code,":[152],"will":[153],"be":[154],"necessary":[155],"for":[156],"robust":[157],"semantic":[158],"understanding.":[159],"Meanwhile,":[160],"practitioners":[161],"achieve":[163],"better":[164],"results":[165],"selecting":[167],"stronger":[168],"models,":[169],"carefully":[170],"engineering":[171],"prom-pts,":[172],"writing":[174],"tools":[177],"normalize":[179],"low-level":[180],"differences":[181],"before":[182],"inference.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-18T05:51:51.687321","created_date":"2026-03-28T00:00:00"}
