{"id":"https://openalex.org/W7224765208","doi":"https://doi.org/10.48550/arxiv.2610.39519","title":"Lost in the Latent Space: How Code Embeddings Represent Functional Intent and Implementation Fidelity","display_name":"Lost in the Latent Space: How Code Embeddings Represent Functional Intent and Implementation Fidelity","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224765208","doi":"https://doi.org/10.48550/arxiv.2610.39519"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39519","pdf_url":"https://arxiv.org/pdf/2610.39519","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39519","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160214601","display_name":"Lu Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sun, Lu","raw_affiliation_strings":["The University of Tokyo , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160153130","display_name":"Yuheng Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huang, Yuheng","raw_affiliation_strings":["The University of Tokyo , Tokyo , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160163297","display_name":"Lei Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["CA","JP"],"is_corresponding":false,"raw_author_name":"Ma, Lei","raw_affiliation_strings":["The University of Tokyo , Tokyo , Japan","University of Alberta , Edmonton , AB , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo , Tokyo , Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Alberta , Edmonton , AB , Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160220931","display_name":"Zhijie Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wang, Zhijie","raw_affiliation_strings":["Concordia University , Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University , Montreal , QC , Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code-embeddings","display_name":"code embeddings","score":0.9409999847412109},{"id":"https://openalex.org/keywords/latent-representations","display_name":"latent representations","score":0.6399999856948853},{"id":"https://openalex.org/keywords/functional-abstraction","display_name":"functional abstraction","score":0.9229999780654907},{"id":"https://openalex.org/keywords/implementation-fidelity","display_name":"implementation fidelity","score":0.9959999918937683},{"id":"https://openalex.org/keywords/probing","display_name":"probing","score":0.6349999904632568},{"id":"https://openalex.org/keywords/semantic-generalization","display_name":"semantic generalization","score":0.8399999737739563}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7849000096321106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803999781608582},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6596999764442444},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5954999923706055},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4027000069618225},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.376800000667572},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.34150001406669617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39519","pdf_url":"https://arxiv.org/pdf/2610.39519","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.2610.39519","doi":"https://doi.org/10.48550/arxiv.2610.39519","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39519","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:2610.39519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39519","pdf_url":"https://arxiv.org/pdf/2610.39519","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224765208.pdf","grobid_xml":"https://content.openalex.org/works/W7224765208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7129281073","https://openalex.org/W4400518683","https://openalex.org/W4221061332","https://openalex.org/W4388716357","https://openalex.org/W4388483278","https://openalex.org/W3198956694","https://openalex.org/W4415989254","https://openalex.org/W4372260112","https://openalex.org/W6922652885","https://openalex.org/W4282033849"],"abstract_inverted_index":{"Code":[0],"embedding":[1,37,60,92,162],"models":[2,105,124,163],"have":[3],"become":[4],"a":[5,35,52,101,144],"key":[6],"building":[7],"block":[8],"for":[9,73],"many":[10],"software":[11,165],"engineering":[12],"applications,":[13],"yet":[14],"their":[15,64],"internal":[16],"representations":[17],"remain":[18],"poorly":[19],"understood.":[20],"Existing":[21],"evaluations":[22],"tend":[23,113],"to":[24,82,94,114,134],"focus":[25],"on":[26],"downstream":[27],"task":[28],"performance,":[29],"offering":[30],"limited":[31],"insight":[32],"into":[33],"whether":[34],"single":[36,145],"can":[38,129],"support":[39],"both":[40],"functional":[41,74],"abstraction":[42,75],"and":[43,76,86,110,158],"implementation-sensitive":[44],"analysis.":[45],"To":[46],"address":[47],"this":[48],"gap,":[49],"we":[50],"present":[51],"large-scale":[53],"empirical":[54],"study":[55],"of":[56,120,151,160],"14":[57],"state-of-the-art":[58],"code":[59,96,147,161],"models.":[61],"We":[62],"evaluate":[63],"representational":[65],"behavior":[66],"through":[67],"three":[68],"complementary":[69],"analyses:":[70],"supervised":[71],"probing":[72],"implementation":[77,137],"fidelity,":[78],"zero-shot":[79],"retrieval":[80,127],"experiments":[81,89],"assess":[83],"geometric":[84],"similarity,":[85],"controlled":[87],"perturbation":[88],"that":[90,106,143],"measure":[91],"responses":[93],"semantics-preserving":[95],"transformations.":[97],"The":[98],"results":[99],"reveal":[100],"consistent":[102],"abstraction-fidelity":[103],"tension:":[104],"better":[107],"preserve":[108],"stylistic":[109],"structural":[111],"signals":[112],"do":[115],"so":[116],"at":[117],"the":[118,135],"expense":[119],"semantic":[121],"generalization,":[122],"while":[123],"with":[125],"similar":[126],"performance":[128],"nevertheless":[130],"respond":[131],"very":[132],"differently":[133],"same":[136],"changes.":[138],"Overall,":[139],"our":[140],"findings":[141],"suggest":[142],"universal":[146],"representation":[148],"remains":[149],"out":[150],"reach,":[152],"motivating":[153],"more":[154],"representation-aware":[155],"evaluation,":[156],"selection,":[157],"deployment":[159],"in":[164],"engineering.":[166]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}