{"id":"https://openalex.org/W7161134057","doi":"https://doi.org/10.48550/arxiv.2605.13501","title":"Reward-Weighted On-Policy Distillation with an Open Property-Equivalence Verifier for NL-to-SVA Generation","display_name":"Reward-Weighted On-Policy Distillation with an Open Property-Equivalence Verifier for NL-to-SVA Generation","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161134057","doi":"https://doi.org/10.48550/arxiv.2605.13501"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13501","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.13501","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120765814","display_name":"Qingyun Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Qingyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017403079","display_name":"Y. X. Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yingze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063281095","display_name":"Tianen Liu","orcid":"https://orcid.org/0000-0003-3817-2839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tianen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136128507","display_name":"Bingsheng He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Bingsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wong, Weng-Fai","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/T10028","display_name":"Topic Modeling","score":0.28529998660087585,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.28529998660087585,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09730000048875809,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.08659999817609787,"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/liveness","display_name":"Liveness","score":0.9085000157356262},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6291000247001648},{"id":"https://openalex.org/keywords/mimicry","display_name":"Mimicry","score":0.6240000128746033},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5685999989509583},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.524399995803833},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5206000208854675},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4893999993801117}],"concepts":[{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.9085000157356262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168999910354614},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6291000247001648},{"id":"https://openalex.org/C7863114","wikidata":"https://www.wikidata.org/wiki/Q192627","display_name":"Mimicry","level":2,"score":0.6240000128746033},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4675999879837036},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13501","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.13501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13501","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5359815955162048}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM-based":[0],"generation":[1],"of":[2,141],"SystemVerilog":[3],"Assertions":[4],"(SVA)":[5],"is":[6,51],"often":[7],"reported":[8],"as":[9],"nearing":[10],"saturation,":[11],"with":[12,89],"the":[13,53,66,112,142],"strongest":[14],"specialized":[15,155],"model":[16],"reaching":[17],"${\\sim}76\\%$":[18],"accuracy":[19],"on":[20,43,58,107,144],"NL2SVA-Human.":[21],"We":[22,73],"show":[23],"that":[24,32,52,69,83,136],"this":[25],"aggregate":[26],"hides":[27],"a":[28,39,98,103,133,138],"temporal":[29],"gap:":[30],"models":[31,158],"appear":[33],"strong":[34],"overall":[35],"still":[36],"collapse":[37],"to":[38],"few":[40],"implication":[41],"templates":[42],"bounded-delay":[44],"and":[45,96,123,146,151,159],"liveness":[46],"specifications.":[47],"The":[48],"core":[49],"issue":[50],"dominant":[54],"recipe,":[55],"supervised":[56],"fine-tuning":[57],"NL/SVA":[59],"pairs,":[60],"optimizes":[61],"token-level":[62],"mimicry":[63],"rather":[64],"than":[65],"\\emph{property":[67],"equivalence}":[68],"defines":[70],"SVA":[71],"correctness.":[72],"introduce":[74],"\\emph{Reward-Weighted":[75],"On-Policy":[76],"Distillation}":[77],"(RWOPD),":[78],"an":[79,90],"on-policy":[80],"distillation":[81],"method":[82],"samples":[84],"student":[85,135],"rollouts,":[86],"scores":[87],"them":[88],"open":[91],"SymbiYosys+Z3":[92],"Property-Equivalence":[93],"Checker":[94],"(PEC),":[95],"applies":[97],"verifier-reward-weighted":[99],"forward-KL":[100],"gradient":[101],"from":[102],"frozen":[104],"14B":[105],"teacher":[106],"verifier-passable":[108],"rollouts.":[109],"This":[110],"keeps":[111],"supervision":[113],"dense":[114],"at":[115],"every":[116],"response":[117],"token":[118],"while":[119],"grounding":[120],"both":[121,154],"selection":[122],"loss":[124],"weight":[125],"in":[126],"property-equivalent":[127],"behavior.":[128],"RWOPD":[129],"distills":[130],"CodeV-SVA-14B":[131],"into":[132],"Qwen2.5-Coder-7B-Instruct":[134],"sets":[137],"new":[139],"state":[140],"art":[143],"NL2SVA-Human":[145],"NL2SVA-Machine":[147],"across":[148],"pass@1,":[149],"pass@5,":[150],"pass@10,":[152],"surpassing":[153],"prior":[156],"SOTA":[157],"671B":[160],"general-purpose":[161],"baselines.":[162]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-15T00:00:00"}