{"id":"https://openalex.org/W7203928858","doi":"https://doi.org/10.48550/arxiv.2608.18294","title":"Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements","display_name":"Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203928858","doi":"https://doi.org/10.48550/arxiv.2608.18294"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.18294","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18294","pdf_url":"https://arxiv.org/pdf/2608.18294","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":"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/2608.18294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041445378","display_name":"Naoki Egami","orcid":"https://orcid.org/0000-0002-5491-2174","observed_orcids":["https://orcid.org/0000-0002-5491-2174"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Egami, Naoki","raw_affiliation_strings":["Associate Professor, Department of Political Science and Statistics and Data Science Center , Massachusetts Insti- tute of Technology , Cambridge , MA 02139 "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Associate Professor, Department of Political Science and Statistics and Data Science Center , Massachusetts Insti- tute of Technology , Cambridge , MA 02139 ","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062025993","display_name":"Sooahn Shin","orcid":"https://orcid.org/0000-0001-6213-2197","observed_orcids":["https://orcid.org/0000-0001-6213-2197"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shin, Sooahn","raw_affiliation_strings":["Postdoctoral Associate, Department of Political Science , Massachusetts Institute of Technology , Cambridge , MA 02139 "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Postdoctoral Associate, Department of Political Science , Massachusetts Institute of Technology , Cambridge , MA 02139 ","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.5576000213623047,"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":0.5576000213623047,"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":0.23240000009536743,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.027899999171495438,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-generated-data","display_name":"AI-generated data","score":0.796999990940094},{"id":"https://openalex.org/keywords/automatic-measurement","display_name":"automated measurement","score":0.6179999709129333},{"id":"https://openalex.org/keywords/measurement-error","display_name":"measurement error","score":0.6169999837875366},{"id":"https://openalex.org/keywords/large-language-model-annotation","display_name":"large language model annotation","score":0.6399999856948853},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"conditional independence","score":0.47200000286102295},{"id":"https://openalex.org/keywords/cp-decomposition","display_name":"CP decomposition","score":0.6389999985694885},{"id":"https://openalex.org/keywords/semiparametric-inference","display_name":"semiparametric inference","score":0.8220000267028809},{"id":"https://openalex.org/keywords/misclassification-rate","display_name":"misclassification rate","score":0.6919999718666077},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.6539999842643738},{"id":"https://openalex.org/keywords/confidence-intervals","display_name":"confidence intervals","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7889999747276306},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.7384999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485999822616577},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340999960899353},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.36340001225471497},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.29280000925064087},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.18294","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18294","pdf_url":"https://arxiv.org/pdf/2608.18294","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.18294","doi":"https://doi.org/10.48550/arxiv.2608.18294","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.18294","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:2608.18294","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18294","pdf_url":"https://arxiv.org/pdf/2608.18294","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203928858.pdf","grobid_xml":"https://content.openalex.org/works/W7203928858.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4388327685","https://openalex.org/W4392223431","https://openalex.org/W4396986912","https://openalex.org/W4415315423","https://openalex.org/W4417071108","https://openalex.org/W4417136306","https://openalex.org/W6948325277","https://openalex.org/W7128815885","https://openalex.org/W7160960408","https://openalex.org/W7164890227"],"related_works":["https://openalex.org/W7154743086","https://openalex.org/W7169780357","https://openalex.org/W7204159052","https://openalex.org/W7154965379","https://openalex.org/W7167728803","https://openalex.org/W7133232943","https://openalex.org/W7162773354","https://openalex.org/W7128704716","https://openalex.org/W7162578843","https://openalex.org/W7123312012"],"abstract_inverted_index":{"An":[0],"increasing":[1],"number":[2],"of":[3,162,192,224],"scholars":[4],"use":[5,170],"AI":[6,46,101],"to":[7,34,77,103,150,174,233],"measure":[8],"variables":[9,18],"they":[10],"subsequently":[11],"include":[12],"in":[13,30,41,79,197],"downstream":[14,42,106,193],"analyses.":[15],"Although":[16],"AI-measured":[17],"are":[19,124],"often":[20],"analyzed":[21],"as":[22,57,137],"if":[23,45],"observed":[24,133],"without":[25,108],"error,":[26],"ignoring":[27],"prediction":[28],"errors":[29],"automated":[31],"measurement":[32,47],"leads":[33],"substantial":[35],"bias":[36],"and":[37,61,75,132,159,182,210],"invalid":[38],"confidence":[39],"intervals":[40],"analyses,":[43],"even":[44],"accuracy":[48],"is":[49,180],"high,":[50],"e.g.,":[51],"above":[52],"90%.":[53],"Existing":[54],"solutions,":[55],"such":[56,136],"design-based":[58],"supervised":[59],"learning":[60],"prediction-powered":[62],"inference,":[63],"combine":[64],"error-prone":[65,100],"AI-based":[66],"measurements":[67,93,102,123,216],"with":[68,90],"gold-standard":[69,109],"labels,":[70],"which":[71],"may":[72],"be":[73],"costly":[74],"difficult":[76],"obtain":[78],"some":[80],"application":[81],"areas.":[82],"In":[83],"this":[84,167],"paper,":[85],"we":[86,169,229],"propose":[87],"debiased":[88],"inference":[89,107,172,187,209],"multiple":[91,99],"imperfect":[92],"(DMM),":[94],"a":[95,189],"framework":[96,144],"that":[97,121,176,205,211],"combines":[98],"enable":[104],"valid":[105,186,208],"labels.":[110],"Building":[111],"on":[112,116,127,221],"the":[113,128,177,198,235],"established":[114],"results":[115,203],"CP":[117],"decomposition,":[118],"DMM":[119,178,206],"assumes":[120],"these":[122],"independent":[125],"conditional":[126,236],"latent":[129],"true":[130],"label":[131],"unit-level":[134],"features,":[135],"text":[138],"features":[139],"represented":[140],"by":[141],"embeddings.":[142],"This":[143],"allows":[145],"for":[146,188],"unknown":[147],"misclassification":[148],"rates":[149],"vary":[151],"across":[152,160],"annotation":[153,163],"methods":[154],"(e.g.,":[155,164],"large":[156,225],"language":[157,226],"models)":[158],"units":[161],"texts).":[165],"Under":[166],"assumption,":[168],"semiparametric":[171],"theory":[173],"prove":[175],"estimator":[179],"consistent":[181],"asymptotically":[183],"normal,":[184],"enabling":[185],"wide":[190],"range":[191],"statistical":[194],"analyses":[195],"common":[196,222],"social":[199],"sciences.":[200],"Our":[201],"simulation":[202],"show":[204],"yields":[207],"adding":[212],"accurate,":[213],"though":[214],"imperfect,":[215],"can":[217],"improve":[218],"efficiency.":[219],"Focusing":[220],"applications":[223],"model":[227],"annotations,":[228],"also":[230],"develop":[231],"diagnostics":[232],"assess":[234],"independence":[237],"assumption.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-22T00:00:00"}