{"id":"https://openalex.org/W7204254129","doi":"https://doi.org/10.48550/arxiv.2608.24218","title":"Constraint-Guided Enterprise Data Mapping with Large Language Models","display_name":"Constraint-Guided Enterprise Data Mapping with Large Language Models","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204254129","doi":"https://doi.org/10.48550/arxiv.2608.24218"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.24218","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24218","pdf_url":"https://arxiv.org/pdf/2608.24218","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/2608.24218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065068289","display_name":"Sebastian Monka","orcid":"https://orcid.org/0009-0006-7983-1625","observed_orcids":["https://orcid.org/0009-0006-7983-1625"]},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Monka, Sebastian","raw_affiliation_strings":["Bosch Center for Artificial Intelligence , Renningen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence , Renningen , Germany","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010060555","display_name":"Pramod Anantharam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anantharam, Pramod","raw_affiliation_strings":["Bosch Center for Artificial Intel- ligence , Pittsburgh , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intel- ligence , Pittsburgh , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148318308","display_name":"Thien Vo Minh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minh, Thien Vo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031926202","display_name":"Lavdim Halilaj","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Halilaj, Lavdim","raw_affiliation_strings":["Bosch Center for Artificial Intelligence , Renningen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence , Renningen , Germany","institution_ids":["https://openalex.org/I889804353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T11719","display_name":"Data Quality and Management","score":0.9351000189781189,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9351000189781189,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.042399998754262924,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.008700000122189522,"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/entity-alignment","display_name":"entity alignment","score":0.9729999899864197},{"id":"https://openalex.org/keywords/admissibility-constraints","display_name":"admissibility constraints","score":0.9200000166893005},{"id":"https://openalex.org/keywords/candidate-generation","display_name":"candidate generation","score":0.48899999260902405},{"id":"https://openalex.org/keywords/neural-ranking","display_name":"neural ranking","score":0.718999981880188},{"id":"https://openalex.org/keywords/structural-invariants","display_name":"structural invariants","score":0.6940000057220459},{"id":"https://openalex.org/keywords/cross-dataset-transfer","display_name":"cross-dataset transfer","score":0.453000009059906},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722599983215332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35429999232292175},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.26019999384880066}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24218","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24218","pdf_url":"https://arxiv.org/pdf/2608.24218","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.2608.24218","doi":"https://doi.org/10.48550/arxiv.2608.24218","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24218","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24218","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24218","pdf_url":"https://arxiv.org/pdf/2608.24218","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204254129.pdf","grobid_xml":"https://content.openalex.org/works/W7204254129.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Enterprise":[0],"entity":[1],"alignment":[2],"must":[3],"handle":[4],"semi-structured":[5],"records,":[6],"implicit":[7],"attributes,":[8],"and":[9,27,39,74,79,97,125,146,168,213,231],"unit":[10],"or":[11],"granularity":[12],"mismatches.":[13],"Manual":[14],"matching":[15,31],"is":[16,156,166],"still":[17],"common":[18],"in":[19],"practice,":[20],"but":[21],"does":[22],"not":[23,153,192],"scale":[24],"as":[25,113],"schemas":[26],"providers":[28],"evolve.":[29],"LLM-only":[30],"improves":[32],"semantic":[33],"recall,":[34],"yet":[35,44],"can":[36],"violate":[37],"structural":[38,241],"physical":[40],"invariants,":[41],"producing":[42],"fluent":[43],"operationally":[45],"invalid":[46],"correspondences.":[47],"We":[48],"propose":[49],"constraint-guided":[50],"mapping":[51],"(CGM),":[52],"a":[53,91,130,147,174,180,193],"neuro-symbolic":[54],"method":[55],"with":[56,63,86,101,177],"three":[57],"stages:":[58],"(i)":[59],"schema-grounded":[60],"admissibility":[61,135],"constraints":[62,111,178,235],"metadata":[64],"mc":[65],"=":[66],",":[67],"where":[68,240],"tau_c":[69],"denotes":[70],"the":[71,137,144,154,157,233],"constraint":[72],"type":[73],"delta_c":[75],"provides":[76],"executable":[77],"relation":[78],"normalization":[80],"logic;":[81],"(ii)":[82],"constraint-restricted":[83],"candidate":[84,138],"generation":[85],"cascade":[87],"relaxation":[88,124],"to":[89,106,162],"guarantee":[90],"nonempty":[92],"feasible":[93,108],"set":[94],"under":[95,123,206],"noise;":[96],"(iii)":[98],"neural":[99],"ranking":[100,228],"bounded":[102],"LLM":[103,182],"disambiguation":[104],"restricted":[105],"that":[107],"set.":[109],"Methodologically,":[110],"operate":[112],"hypothesis-space":[114],"operators":[115],"rather":[116],"than":[117],"post-hoc":[118],"validators,":[119],"enabling":[120],"controlled":[121,131],"degradation":[122],"auditable,":[126],"human-guidable":[127],"decisions.":[128],"On":[129],"structural-decoy":[132],"benchmark,":[133],"hard":[134,238],"shrinks":[136],"space":[139],"by":[140,217],"~480x":[141],"without":[142,184],"dropping":[143],"GT,":[145],"layer-by-layer":[148],"ablation":[149],"shows":[150],"this":[151],"gate,":[152],"LLM,":[155],"decisive":[158],"lift":[159],"(F1":[160],"0.08":[161],"0.66).":[163],"The":[164,190],"benefit":[165],"model-independent":[167],"adds":[169],"no":[170],"extra":[171],"inference":[172],"cost:":[173],"small":[175],"model":[176],"matches":[179],"frontier":[181],"used":[183],"them":[185],"at":[186],"~28x":[187],"lower":[188],"cost.":[189],"method,":[191],"single":[194],"tuned":[195],"configuration,":[196],"transfers":[197],"across":[198],"seven":[199],"enterprise":[200],"makes":[201],"(macro":[202],"F1":[203],"0.70),":[204],"each":[205],"its":[207],"own":[208],"automatically":[209],"discovered,":[210],"expert-refinable":[211],"constraints,":[212],"lowers":[214],"expert":[215],"effort":[216],"~7x":[218],"versus":[219],"spreadsheet":[220],"workflows.":[221],"Public":[222],"Valentine":[223],"results":[224],"add":[225],"an":[226],"external":[227],"sanity":[229],"check":[230],"mark":[232],"boundary:":[234],"should":[236],"be":[237],"only":[239],"invariants":[242],"are":[243],"match-determining.":[244]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-08-27T00:00:00"}