{"id":"https://openalex.org/W7152555897","doi":"https://doi.org/10.48550/arxiv.2604.06485","title":"Inference-Time Code Selection via Symbolic Equivalence Partitioning","display_name":"Inference-Time Code Selection via Symbolic Equivalence Partitioning","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7152555897","doi":"https://doi.org/10.48550/arxiv.2604.06485"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06485","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.06485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133270994","display_name":"David Cho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cho, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133242863","display_name":"Yifan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018927509","display_name":"Fanping Sui","orcid":"https://orcid.org/0009-0004-4040-0639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sui, Fanping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019202832","display_name":"Ananth Grama","orcid":"https://orcid.org/0000-0002-9378-9244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grama, Ananth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.2574000060558319,"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":0.2574000060558319,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.17419999837875366,"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/T10028","display_name":"Topic Modeling","score":0.11100000143051147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/satisfiability-modulo-theories","display_name":"Satisfiability modulo theories","score":0.7552000284194946},{"id":"https://openalex.org/keywords/symbolic-execution","display_name":"Symbolic execution","score":0.7373999953269958},{"id":"https://openalex.org/keywords/modulo","display_name":"Modulo","score":0.5855000019073486},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.58160001039505},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.548799991607666},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47909998893737793},{"id":"https://openalex.org/keywords/satisfiability","display_name":"Satisfiability","score":0.4487999975681305},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4221000075340271},{"id":"https://openalex.org/keywords/symbolic-data-analysis","display_name":"Symbolic data analysis","score":0.41780000925064087}],"concepts":[{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.7552000284194946},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.7373999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662999987602234},{"id":"https://openalex.org/C54732982","wikidata":"https://www.wikidata.org/wiki/Q1415345","display_name":"Modulo","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C168773769","wikidata":"https://www.wikidata.org/wiki/Q1350299","display_name":"Satisfiability","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.39169999957084656},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2776400721","wikidata":"https://www.wikidata.org/wiki/Q18171762","display_name":"Symbolic regression","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C23123167","wikidata":"https://www.wikidata.org/wiki/Q7661193","display_name":"Symbolic trajectory evaluation","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C6943359","wikidata":"https://www.wikidata.org/wiki/Q875276","display_name":"Boolean satisfiability problem","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C11219265","wikidata":"https://www.wikidata.org/wiki/Q5158734","display_name":"Concolic testing","level":4,"score":0.25279998779296875},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06485","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06485","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sampling":[0],"multiple":[1],"candidate":[2,115],"programs":[3,116],"at":[4],"inference":[5],"time":[6],"is":[7,67,172],"an":[8,92,173],"effective":[9,174],"way":[10],"to":[11,53,111,156,163],"improve":[12],"LLM":[13,146],"code":[14,178],"generation.":[15],"However,":[16],"its":[17],"benefit":[18],"depends":[19],"on":[20,158,165],"reliably":[21],"selecting":[22],"a":[23,37],"correct":[24,41],"solution":[25],"from":[26,124,154,161],"the":[27,54,62,82,113,125],"generated":[28],"pool.":[29],"We":[30,86],"observe":[31],"that":[32,80,96,168],"this":[33],"selection":[34,94,136],"problem":[35],"has":[36],"distinctive":[38],"semantic":[39],"structure:":[40],"solutions,":[42],"despite":[43],"differences":[44],"in":[45],"syntax,":[46],"implementation,":[47],"or":[48,144],"algorithmic":[49],"strategy,":[50],"often":[51],"converge":[52],"same":[55,63,83],"functional":[56,119,170],"behavior":[57],"over":[58],"valid":[59],"inputs.":[60],"At":[61,148],"time,":[64],"consensus":[65],"alone":[66],"not":[68],"sufficient":[69],"for":[70,176],"correctness,":[71],"because":[72],"models":[73],"can":[74],"also":[75],"produce":[76],"correlated":[77],"wrong":[78],"solutions":[79],"implement":[81],"mistaken":[84],"behavior.":[85],"propose":[87],"Symbolic":[88],"Equivalence":[89],"Partitioning":[90],"(SEP),":[91],"inference-time":[93,177],"framework":[95],"first":[97],"uses":[98,108],"problem-provided":[99],"public":[100],"examples":[101],"as":[102],"lightweight":[103],"validity":[104],"signals.":[105],"SEP":[106,133,150],"then":[107],"symbolic":[109,169],"execution":[110],"partition":[112],"remaining":[114],"into":[117],"bounded":[118],"equivalence":[120,127],"classes":[121],"and":[122,131,160],"selects":[123],"dominant":[126],"class.":[128],"Across":[129],"HumanEval+":[130,159],"LiveCodeBench,":[132,166],"consistently":[134],"improves":[135,151],"accuracy":[137,153],"without":[138],"auxiliary":[139],"test":[140],"generation,":[141],"learned":[142],"verifiers,":[143],"additional":[145],"inference.":[147],"$N=10$,":[149],"average":[152],"0.754":[155],"0.826":[157],"0.565":[162],"0.647":[164],"showing":[167],"agreement":[171],"signal":[175],"selection.":[179]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-10T00:00:00"}