{"id":"https://openalex.org/W7212079252","doi":"https://doi.org/10.48550/arxiv.2609.07987","title":"When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability","display_name":"When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability","publication_year":2026,"publication_date":"2026-09-07","ids":{"openalex":"https://openalex.org/W7212079252","doi":"https://doi.org/10.48550/arxiv.2609.07987"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.07987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07987","pdf_url":"https://arxiv.org/pdf/2609.07987","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/2609.07987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150934902","display_name":"Steven Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Steven","raw_affiliation_strings":["University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077822203","display_name":"Kyle Hunt","orcid":"https://orcid.org/0000-0002-7847-9715","observed_orcids":["https://orcid.org/0000-0002-7847-9715"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hunt, Kyle","raw_affiliation_strings":["University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150944122","display_name":"Shaojie Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tang, Shaojie","raw_affiliation_strings":["University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5151030564","display_name":"Kenneth Joseph","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph, Kenneth","raw_affiliation_strings":["University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.47780001163482666,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.47780001163482666,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.07699999958276749,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.053300000727176666,"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/behavioral-fidelity","display_name":"behavioral fidelity","score":0.7799999713897705},{"id":"https://openalex.org/keywords/prediction-powered-inference","display_name":"prediction-powered inference","score":0.7599999904632568},{"id":"https://openalex.org/keywords/population-stability","display_name":"population stability","score":0.5799999833106995},{"id":"https://openalex.org/keywords/ai-generated-evidence","display_name":"AI-generated evidence","score":0.6209999918937683},{"id":"https://openalex.org/keywords/validity-of-inference","display_name":"validity of inference","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C2776640315","wikidata":"https://www.wikidata.org/wiki/Q7315941","display_name":"Respondent","level":2,"score":0.675000011920929},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6743000149726868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029999852180481},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.536899983882904},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3330000042915344},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C2778058735","wikidata":"https://www.wikidata.org/wiki/Q4692253","display_name":"Aggregate data","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C188255311","wikidata":"https://www.wikidata.org/wiki/Q7256388","display_name":"Psychological research","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C5570062","wikidata":"https://www.wikidata.org/wiki/Q3919817","display_name":"Behavioural sciences","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2778864079","wikidata":"https://www.wikidata.org/wiki/Q173285","display_name":"Digital data","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C84679943","wikidata":"https://www.wikidata.org/wiki/Q1925442","display_name":"Common-method variance","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.07987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07987","pdf_url":"https://arxiv.org/pdf/2609.07987","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.2609.07987","doi":"https://doi.org/10.48550/arxiv.2609.07987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.07987","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.07987","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.07987","pdf_url":"https://arxiv.org/pdf/2609.07987","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/W7212079252.pdf","grobid_xml":"https://content.openalex.org/works/W7212079252.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4388327685","https://openalex.org/W4392340310","https://openalex.org/W4404569548","https://openalex.org/W4415318313","https://openalex.org/W4416786397","https://openalex.org/W4417080482","https://openalex.org/W7130415382"],"related_works":["https://openalex.org/W7212724587","https://openalex.org/W7083013479","https://openalex.org/W7167372022","https://openalex.org/W7161178016","https://openalex.org/W7206210237","https://openalex.org/W4416254488","https://openalex.org/W7154412893","https://openalex.org/W7223174837","https://openalex.org/W7129589649","https://openalex.org/W4417288494"],"abstract_inverted_index":{"LLM-based":[0],"digital":[1,107],"twins":[2,108,206],"promise":[3],"to":[4,46,157,191,200],"reduce":[5,25,51,147,217],"repeated":[6],"human":[7,26,52,112,202,220,228],"data":[8],"collection":[9],"by":[10,214,224],"generating":[11],"person-":[12],"specific":[13],"responses,":[14],"yet":[15,151],"existing":[16],"evaluations":[17,94],"provide":[18],"little":[19,116],"evidence":[20,183],"about":[21,118,219],"whether":[22,215,225],"they":[23,179,216,226],"can":[24,50,109,146],"measurement":[27,53],"while":[28,58,114],"preserving":[29,59],"valid":[30,60,193],"inference.":[31,61],"To":[32],"address":[33],"this,":[34],"we":[35,104],"introduce":[36],"statistical":[37,74,175],"substitutability,":[38],"an":[39],"inferential":[40],"criterion":[41],"that":[42,72,106,166,181],"evaluates":[43,73],"the":[44],"extent":[45],"which":[47,119],"twin":[48],"predictions":[49],"for":[54,174,211],"a":[55,64],"particular":[56],"estimand":[57],"We":[62],"develop":[63],"framework,":[65],"grounded":[66],"in":[67],"mixed-subject":[68],"and":[69,87,100,127],"prediction-powered":[70],"inference,":[71],"substitutability":[75],"along":[76],"four":[77],"dimensions:":[78],"aggregate":[79,148],"fidelity,":[80],"paired":[81],"respondent-level":[82],"signal,":[83],"finite-sample":[84],"human-label":[85],"recovery,":[86],"stability":[88],"across":[89],"populations.":[90],"Across":[91],"two":[92],"empirical":[93],"spanning":[95],"behavioral":[96,167],"experiments,":[97],"multiple":[98],"models,":[99],"alternative":[101],"respondent":[102,129],"representations,":[103],"find":[105],"reproduce":[110,201,227],"average":[111],"effects":[113],"providing":[115],"information":[117,130],"individuals":[120],"differ":[121],"from":[122],"those":[123],"averages.":[124],"Newer":[125],"models":[126],"richer":[128],"improve":[131],"some":[132],"dimensions":[133],"of":[134],"performance":[135],"but":[136],"do":[137],"not":[138,222],"reliably":[139],"translate":[140],"into":[141],"human-data":[142],"savings.":[143],"Human":[144],"calibration":[145],"prediction":[149],"error,":[150],"limited":[152],"labeled":[153],"samples":[154],"often":[155],"fail":[156],"produce":[158],"stable":[159],"precision":[160],"gains.":[161],"Importantly,":[162],"these":[163],"findings":[164],"demonstrate":[165],"fidelity":[168],"is":[169],"neither":[170],"necessary":[171],"nor":[172],"sufficient":[173],"substitutability.":[176],"More":[177],"broadly,":[178],"suggest":[180],"AI-generated":[182],"should":[184,207],"be":[185,209],"evaluated":[186],"based":[187],"on":[188],"its":[189,198],"ability":[190,199],"support":[192],"scientific":[194],"inference":[195],"rather":[196],"than":[197],"outcomes":[203],"alone.":[204],"Digital":[205],"therefore":[208],"judged":[210],"confirmatory":[212],"use":[213],"uncertainty":[218],"quantities,":[221],"merely":[223],"means,":[229],"distributions,":[230],"or":[231],"effects.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-10T00:00:00"}