{"id":"https://openalex.org/W7214726148","doi":"https://doi.org/10.48550/arxiv.2609.32431","title":"DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation","display_name":"DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214726148","doi":"https://doi.org/10.48550/arxiv.2609.32431"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32431","pdf_url":"https://arxiv.org/pdf/2609.32431","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.32431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101953092","display_name":"Shenghao Li","orcid":"https://orcid.org/0000-0002-8968-7333","observed_orcids":["https://orcid.org/0000-0002-8968-7333"]},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Shenghao","raw_affiliation_strings":["Guangzhou University , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou University , Guangzhou , China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153450179","display_name":"Lin Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Lin","raw_affiliation_strings":["Guangzhou University , Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou University , Guangzhou , China","institution_ids":["https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37987034"],"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/T10028","display_name":"Topic Modeling","score":0.8306000232696533,"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":0.8306000232696533,"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":0.052400000393390656,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.013700000010430813,"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/data-augmentation","display_name":"data augmentation","score":0.7229999899864197},{"id":"https://openalex.org/keywords/quality-control","display_name":"quality control","score":0.7649999856948853},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.953000009059906},{"id":"https://openalex.org/keywords/semantic-verification","display_name":"semantic verification","score":0.5419999957084656},{"id":"https://openalex.org/keywords/symbolic-verification","display_name":"symbolic verification","score":0.9929999709129333},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"anomaly detection","score":0.5419999957084656},{"id":"https://openalex.org/keywords/data-repair","display_name":"data repair","score":0.5339999794960022},{"id":"https://openalex.org/keywords/z3-smt-solver","display_name":"Z3 SMT solver","score":0.5230000019073486},{"id":"https://openalex.org/keywords/execution-history","display_name":"execution history","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569000124931335},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4684999883174896},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4255000054836273},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32431","pdf_url":"https://arxiv.org/pdf/2609.32431","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.2609.32431","doi":"https://doi.org/10.48550/arxiv.2609.32431","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32431","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:2609.32431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32431","pdf_url":"https://arxiv.org/pdf/2609.32431","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/W7214726148.pdf","grobid_xml":"https://content.openalex.org/works/W7214726148.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7104255061","https://openalex.org/W7140928798","https://openalex.org/W4412888502","https://openalex.org/W6929291004","https://openalex.org/W7128219784","https://openalex.org/W4412945707","https://openalex.org/W4403885188","https://openalex.org/W4416035451","https://openalex.org/W4416126058","https://openalex.org/W4412887934"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"provide":[3],"a":[4,17,46,53,69,142],"practical":[5],"way":[6],"to":[7],"generate":[8],"augmented":[9],"data":[10,75],"for":[11,73,87,180],"logical":[12,27,144],"reasoning":[13],"at":[14],"scale,":[15],"but":[16],"larger":[18],"generation":[19,33,36],"volume":[20],"does":[21],"not":[22],"guarantee":[23],"semantic,":[24],"label,":[25],"or":[26,59],"reliability.":[28],"Existing":[29],"work":[30],"has":[31],"improved":[32],"quality":[34,47],"through":[35],"constraints,":[37],"candidate":[38,54,85],"validation,":[39],"filtering,":[40,90],"and":[41,84,92,110,121,128,136,165,183],"feedback-based":[42],"revision;":[43],"however,":[44],"once":[45],"judgment":[48],"is":[49,146],"available,":[50],"deciding":[51],"whether":[52],"should":[55],"be":[56],"retained,":[57],"filtered,":[58],"repaired":[60],"remains":[61],"an":[62],"important":[63],"control":[64],"problem.":[65],"We":[66],"propose":[67],"DualGuard,":[68],"dual-mode":[70],"quality-control":[71],"framework":[72],"logic-preserving":[74],"augmentation.":[76],"The":[77,95],"first":[78],"mode":[79,97],"uses":[80],"the":[81,153,159,167],"current":[82],"instance":[83],"batch":[86],"selective":[88],"retention,":[89],"attribution,":[91,111],"targeted":[93,126],"feedback.":[94],"second":[96],"accumulates":[98],"cross-instance":[99],"execution":[100],"records":[101],"of":[102,107],"augmentation":[103],"actions":[104],"on":[105,162,171],"top":[106],"per-sample":[108],"diagnosis":[109],"compares":[112],"new":[113],"executions":[114],"against":[115],"each":[116],"action's":[117],"own":[118],"historical":[119],"behavior,":[120],"supports":[122],"retrospective":[123],"anomaly":[124,185],"inspection,":[125],"rollback,":[127],"bounded":[129],"repair.":[130],"Both":[131],"modes":[132],"share":[133],"semantic":[134],"verification":[135,140],"additionally":[137],"use":[138],"symbolic":[139],"when":[141],"reliable":[143],"form":[145],"available.":[147],"Across":[148],"seven":[149],"downstream":[150],"tasks":[151,164],"in":[152],"Two-Stage":[154],"Transfer":[155],"setting,":[156],"DualGuard":[157],"achieves":[158],"highest":[160],"Accuracy":[161],"five":[163],"outperforms":[166],"no-augmentation":[168],"BERT":[169],"baseline":[170],"all":[172],"seven.":[173],"Controlled":[174],"ablations":[175],"further":[176],"show":[177],"complementary":[178],"roles":[179],"Memory,":[181],"Z3,":[182],"history-aware":[184],"control.":[186]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-30T00:00:00"}