{"id":"https://openalex.org/W7162539369","doi":"https://doi.org/10.48550/arxiv.2605.26823","title":"Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoning","display_name":"Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoning","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162539369","doi":"https://doi.org/10.48550/arxiv.2605.26823"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26823","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26823","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.2605.26823","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137091443","display_name":"Yunbo Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Yunbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121519731","display_name":"Ge Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137153415","display_name":"Liming Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Liming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137140911","display_name":"Alexandra Brintrup","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brintrup, Alexandra","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.6273999810218811,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.6273999810218811,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.053700000047683716,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.042500000447034836,"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/supply-chain","display_name":"Supply chain","score":0.5027999877929688},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4447999894618988},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4147000014781952},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3682999908924103},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.3628999888896942},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.35910001397132874},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3407999873161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988999843597412},{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.35910001397132874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26823","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26823","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.2605.26823","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26823","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","score":0.76783287525177,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Synthetic":[0],"data":[1,14,17,22,122,134,157],"offers":[2],"a":[3,65,112,126,139,186],"promising":[4],"solution":[5],"to":[6,23,132,145,158,170,196,207],"two":[7],"persistent":[8],"barriers":[9],"in":[10],"supply":[11,49,77,119],"chain":[12,50,78,120],"analytics:":[13],"scarcity":[15],"and":[16,27,41,60,90,94,164,190],"privacy.":[18],"However,":[19],"for":[20,87,115],"synthetic":[21,118],"support":[24],"operational":[25,106,135,210],"simulation":[26],"decision-making,":[28],"it":[29],"must":[30],"do":[31],"more":[32],"than":[33],"reproduce":[34],"the":[35,44,53,74,167,176,197,208],"statistical":[36],"distributions":[37],"of":[38,76],"real":[39,156],"records,":[40],"also":[42],"preserve":[43],"\\emph{operational":[45],"logic}":[46],"that":[47,63,99],"governs":[48],"processes,":[51],"including":[52],"temporal":[54],"orderings,":[55],"mathematical":[56],"dependencies,":[57],"hierarchical":[58],"taxonomies,":[59],"conditional":[61],"rules":[62],"make":[64],"record":[66],"operationally":[67],"plausible.":[68],"We":[69],"consider":[70],"this":[71],"logic":[72],"as":[73],"``physics''":[75],"data.":[79],"Existing":[80],"tabular":[81,121],"generative":[82],"models":[83],"are":[84],"primarily":[85],"optimized":[86],"distributional":[88],"fidelity":[89],"downstream":[91],"predictive":[92],"utility,":[93],"therefore":[95],"often":[96],"generate":[97],"records":[98],"appear":[100],"statistically":[101],"realistic":[102],"but":[103],"violate":[104],"fundamental":[105],"constraints.":[107],"This":[108],"paper":[109],"introduces":[110],"\\textbf{\\textit{TabKG}},":[111],"knowledge-graph-guided":[113],"framework":[114],"logically":[116],"consistent":[117],"generation.":[123,172],"TabKG":[124,174],"constructs":[125],"\\textbf{\\textit{Column":[127],"Relationship":[128],"Knowledge":[129],"Graph":[130],"(CR-KG)}}":[131],"represent":[133],"dependencies.":[136],"It":[137],"uses":[138,166],"multi-LLM":[140],"ensemble":[141],"with":[142,205],"majority":[143],"voting":[144],"propose":[146],"candidate":[147],"relationships":[148,154],"from":[149],"column":[150],"metadata,":[151],"validates":[152],"these":[153,183],"against":[155],"remove":[159],"hallucinated":[160],"or":[161],"unsupported":[162],"edges,":[163],"then":[165],"validated":[168,198],"CR-KG":[169],"guide":[171],"Specifically,":[173],"compresses":[175],"original":[177],"table":[178],"into":[179],"independent":[180],"columns,":[181],"generates":[182],"columns":[184,194],"using":[185],"latent":[187],"diffusion":[188],"model,":[189],"deterministically":[191],"reconstructs":[192],"dependent":[193],"according":[195],"relationships,":[199],"enforcing":[200],"logical":[201],"consistency":[202],"by":[203],"construction":[204],"respect":[206],"discovered":[209],"rules.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-28T00:00:00"}