{"id":"https://openalex.org/W7161276418","doi":"https://doi.org/10.1016/j.jss.2026.112952","title":"A metamorphic testing perspective on knowledge distillation for language models of code: Does the student deeply mimic the teacher?","display_name":"A metamorphic testing perspective on knowledge distillation for language models of code: Does the student deeply mimic the teacher?","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161276418","doi":"https://doi.org/10.1016/j.jss.2026.112952"},"language":"en","primary_location":{"id":"doi:10.1016/j.jss.2026.112952","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jss.2026.112952","pdf_url":null,"source":{"id":"https://openalex.org/S37879656","display_name":"Journal of Systems and Software","issn_l":"0164-1212","issn":["0164-1212","1873-1228"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems and Software","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.jss.2026.112952","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136237113","display_name":"Md. Abdul Awal","orcid":"https://orcid.org/0009-0006-5760-8211"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Md. Abdul Awal","raw_affiliation_strings":["Department of Computer Science, University of Saskatchewan, 110 Science Pl, Saskatoon, S7N 5C9, Saskatchewan, Canada"],"raw_orcid":"https://orcid.org/0009-0006-5760-8211","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, 110 Science Pl, Saskatoon, S7N 5C9, Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136269879","display_name":"Mrigank Rochan","orcid":null},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mrigank Rochan","raw_affiliation_strings":["Department of Computer Science, University of Saskatchewan, 110 Science Pl, Saskatoon, S7N 5C9, Saskatchewan, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, 110 Science Pl, Saskatoon, S7N 5C9, Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136258446","display_name":"Chanchal K. Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chanchal K. Roy","raw_affiliation_strings":["Department of Computer Science, University of Saskatchewan, 110 Science Pl, Saskatoon, S7N 5C9, Saskatchewan, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, 110 Science Pl, Saskatoon, S7N 5C9, Saskatchewan, Canada","institution_ids":["https://openalex.org/I32625721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5136237113"],"corresponding_institution_ids":["https://openalex.org/I32625721"],"apc_list":{"value":3560,"currency":"USD","value_usd":3560},"apc_paid":{"value":3560,"currency":"USD","value_usd":3560},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71304172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"240","issue":null,"first_page":"112952","last_page":"112952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13447","display_name":"Educational and Psychological Assessments","score":0.13609999418258667,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13447","display_name":"Educational and Psychological Assessments","score":0.13609999418258667,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10021","display_name":"EFL/ESL Teaching and Learning","score":0.08420000225305557,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10959","display_name":"Student Assessment and Feedback","score":0.07569999992847443,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.8155999779701233},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5529999732971191},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.30630001425743103},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.29319998621940613},{"id":"https://openalex.org/keywords/knowledge-engineering","display_name":"Knowledge engineering","score":0.27320000529289246}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.8155999779701233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6279000043869019},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5529999732971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4641000032424927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.412200003862381},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.jss.2026.112952","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jss.2026.112952","pdf_url":null,"source":{"id":"https://openalex.org/S37879656","display_name":"Journal of Systems and Software","issn_l":"0164-1212","issn":["0164-1212","1873-1228"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems and Software","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.jss.2026.112952","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jss.2026.112952","pdf_url":null,"source":{"id":"https://openalex.org/S37879656","display_name":"Journal of Systems and Software","issn_l":"0164-1212","issn":["0164-1212","1873-1228"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems and Software","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8171855807304382,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W1982483659","https://openalex.org/W2041650849","https://openalex.org/W2135841285","https://openalex.org/W2150884987","https://openalex.org/W2294370754","https://openalex.org/W2782311202","https://openalex.org/W2807869594","https://openalex.org/W2919115771","https://openalex.org/W2951165326","https://openalex.org/W2963140444","https://openalex.org/W3007157104","https://openalex.org/W3009751875","https://openalex.org/W3015735225","https://openalex.org/W3034457371","https://openalex.org/W3105966348","https://openalex.org/W3174544005","https://openalex.org/W3204279503","https://openalex.org/W3214897310","https://openalex.org/W4210772589","https://openalex.org/W4214589259","https://openalex.org/W4220722393","https://openalex.org/W4241727697","https://openalex.org/W4285490465","https://openalex.org/W4295362399","https://openalex.org/W4389158416","https://openalex.org/W4389208909","https://openalex.org/W4394745194","https://openalex.org/W4394745253","https://openalex.org/W4402665833","https://openalex.org/W4402754257","https://openalex.org/W4404862388","https://openalex.org/W4404918643","https://openalex.org/W4411449759","https://openalex.org/W4411449970","https://openalex.org/W4411450064","https://openalex.org/W4414445243"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"language":[1,53,212,303],"models":[2,186,213,282,304],"of":[3,13,55,84,99,182,190,210,214,301,305],"code":[4,56,306],"have":[5],"achieved":[6],"state-of-the-art":[7],"performance":[8,144],"across":[9],"a":[10,47,51,60,73,96,169,188,293],"wide":[11],"range":[12],"software":[14],"analytics":[15],"tasks,":[16,201],"but":[17],"their":[18],"practical":[19,294],"deployment":[20],"remains":[21,87],"limited":[22],"due":[23],"to":[24,71,105,132,141,159,241],"high":[25],"computational":[26],"costs,":[27],"slow":[28],"inference":[29],"speeds,":[30],"and":[31,81,102,116,184,204,217,231,269,280],"significant":[32],"environmental":[33],"impact.":[34],"To":[35,119],"address":[36,120],"these":[37],"challenges,":[38],"recent":[39],"research":[40],"has":[41],"increasingly":[42],"explored":[43],"knowledge":[44,224,257,309],"distillation":[45,225,258],"as":[46,90,292],"method":[48],"for":[49,251,296],"compressing":[50],"large":[52],"model":[54,62,75,100,129],"(the":[57,63],"teacher)":[58],"into":[59],"smaller":[61],"student)":[64],"while":[65],"maintaining":[66],"performance.":[67],"However,":[68],"the":[69,78,114,127,135,180,249,256,261,278,298],"degree":[70],"which":[72,149],"student":[74,117,128,185,246,281],"deeply":[76,133],"mimics":[77],"predictive":[79],"behavior":[80],"internal":[82],"representations":[83],"its":[85],"teacher":[86,115,136,183,279],"largely":[88],"unexplored,":[89],"current":[91],"accuracy-based":[92,155],"evaluation":[93,254],"provides":[94],"only":[95],"surface-level":[97],"view":[98],"quality":[101],"often":[103,130],"fails":[104,131],"capture":[106,160],"more":[107],"profound":[108],"discrepancies":[109,161,244],"in":[110,139,162,245],"behavioral":[111,163,176,243,252,272,299],"fidelity":[112,177,253,273,300],"between":[113],"models.":[118],"this":[121],"gap,":[122],"we":[123,165],"empirically":[124],"show":[125,236],"that":[126,173,237,265],"mimic":[134],"model,":[137],"resulting":[138],"up":[140,240],"285%":[142],"greater":[143],"drop":[145],"under":[146,187],"adversarial":[147],"attacks,":[148],"is":[150,267],"not":[151],"captured":[152],"by":[153,178],"traditional":[154],"evaluation.":[156],"In":[157],"addition,":[158],"fidelity,":[164],"propose":[166],"MetaCompress":[167,196,238,266,291],",":[168,219,228,230],"metamorphic":[170,192],"testing":[171],"framework":[172,295],"systematically":[174],"evaluates":[175],"comparing":[179],"outputs":[181],"set":[189],"behavior-preserving":[191],"relations.":[193],"We":[194],"evaluate":[195],"on":[197],"two":[198],"widely":[199],"studied":[200],"clone":[202],"detection":[203],"vulnerability":[205],"prediction,":[206],"using":[207,285],"compressed":[208,302],"versions":[209],"popular":[211],"code,":[215],"CodeBERT":[216],"GraphCodeBERT":[218],"obtained":[220],"via":[221],"three":[222],"different":[223],"techniques:":[226],"Compressor":[227],"AVATAR":[229],"MORPH":[232],".":[233],"The":[234],"results":[235,289],"identifies":[239],"62%":[242],"models,":[247],"underscoring":[248],"need":[250],"within":[255],"pipeline.":[259],"Furthermore,":[260],"ablation":[262],"study":[263],"indicates":[264],"robust":[268],"effectively":[270],"detects":[271],"divergence,":[274],"even":[275],"when":[276],"both":[277],"are":[283],"assessed":[284],"transformed":[286],"inputs.":[287],"These":[288],"position":[290],"evaluating":[297],"derived":[307],"through":[308],"distillation.":[310]},"counts_by_year":[],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2026-05-16T00:00:00"}