{"id":"https://openalex.org/W4404350803","doi":"https://doi.org/10.48550/arxiv.2411.00879","title":"DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room","display_name":"DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4404350803","doi":"https://doi.org/10.48550/arxiv.2411.00879"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.00879","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.00879","pdf_url":"https://arxiv.org/pdf/2411.00879","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.00879","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003860243","display_name":"Tsz-Ho Kwok","orcid":"https://orcid.org/0000-0001-7240-1426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwok, Tung Sum Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108749815","display_name":"Chi\u2010Hua Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chi-hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114637032","display_name":"Guang Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Guang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.38510000705718994,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.38510000705718994,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4534960687160492},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.3378477692604065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4534960687160492},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3378477692604065}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.00879","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.00879","pdf_url":"https://arxiv.org/pdf/2411.00879","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.00879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.00879","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.00879","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.00879","pdf_url":"https://arxiv.org/pdf/2411.00879","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404350803.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Data":[0,3],"collaboration":[1,115],"via":[2],"Clean":[4],"Room":[5],"offers":[6,121],"value":[7],"but":[8],"raises":[9],"privacy":[10],"concerns,":[11],"which":[12,78],"can":[13],"be":[14],"addressed":[15],"through":[16],"synthetic":[17,92],"data":[18,93,127],"and":[19,82,98,108],"multi-table":[20,23,68,109],"synthesizers.":[21,69],"Common":[22],"synthesizers":[24,110],"fail":[25],"to":[26,64,87],"perform":[27],"when":[28],"subjects":[29,48],"occur":[30],"repeatedly":[31],"in":[32,54,114],"both":[33,44,96],"tables.":[34],"This":[35],"is":[36,49],"an":[37],"urgent":[38],"yet":[39],"unresolved":[40],"problem,":[41],"since":[42],"having":[43],"tables":[45],"with":[46],"repeating":[47],"common.":[50],"To":[51],"improve":[52],"performance":[53],"this":[55],"scenario,":[56],"we":[57],"present":[58],"the":[59,73,118],"DEREC":[60,105],"3-step":[61],"pre-processing":[62],"pipeline":[63,120],"generalize":[65],"adaptability":[66],"of":[67],"We":[70],"also":[71],"introduce":[72],"SIMPRO":[74],"3-aspect":[75],"evaluation":[76],"metrics,":[77],"leverage":[79],"conditional":[80],"distribution":[81],"large-scale":[83],"simultaneous":[84],"hypothesis":[85],"testing":[86],"provide":[88],"comprehensive":[89],"feedback":[90],"on":[91],"fidelity":[94],"at":[95],"column":[97],"table":[99],"levels.":[100],"Results":[101],"show":[102],"that":[103],"using":[104],"improves":[106],"fidelity,":[107],"outperform":[111],"single-table":[112],"counterparts":[113],"settings.":[116],"Together,":[117],"DEREC-SIMPRO":[119],"a":[122,130],"robust":[123],"solution":[124],"for":[125],"generalizing":[126],"collaboration,":[128],"promoting":[129],"more":[131],"efficient,":[132],"data-driven":[133],"society.":[134]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-11-14T00:00:00"}
