{"id":"https://openalex.org/W7223293283","doi":"https://doi.org/10.48550/arxiv.2610.31662","title":"Reliable AI-Assisted Decisions via Selective Auditing","display_name":"Reliable AI-Assisted Decisions via Selective Auditing","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223293283","doi":"https://doi.org/10.48550/arxiv.2610.31662"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.31662","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31662","pdf_url":"https://arxiv.org/pdf/2610.31662","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/2610.31662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034642620","display_name":"Isaac Gibbs","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gibbs, Isaac","raw_affiliation_strings":["Department of Statistical Sciences University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159348456","display_name":"Elise L. Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han, Elise L.","raw_affiliation_strings":["Department of Computer Science Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076708141","display_name":"Ryan J. Tibshirani","orcid":"https://orcid.org/0000-0002-2158-8304","observed_orcids":["https://orcid.org/0000-0002-2158-8304"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tibshirani, Ryan J.","raw_affiliation_strings":["Department of Statistics University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032482329","display_name":"Tijana Zrnic","orcid":"https://orcid.org/0000-0002-5112-8632","observed_orcids":["https://orcid.org/0000-0002-5112-8632"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zrnic, Tijana","raw_affiliation_strings":["Departments of Statistics and Management Science & Engineering Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Statistics and Management Science & Engineering Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.7202000021934509,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.7202000021934509,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.0674000009894371,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.042899999767541885,"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/confidence-scores","display_name":"confidence scores","score":0.6209999918937683},{"id":"https://openalex.org/keywords/data-annotation","display_name":"data annotation","score":0.6200000047683716},{"id":"https://openalex.org/keywords/text-annotation","display_name":"textual annotation","score":0.6200000047683716}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7997999787330627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278000116348267},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.7221999764442444},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6525999903678894},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3513999879360199},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.31662","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31662","pdf_url":"https://arxiv.org/pdf/2610.31662","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.2610.31662","doi":"https://doi.org/10.48550/arxiv.2610.31662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.31662","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.31662","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.31662","pdf_url":"https://arxiv.org/pdf/2610.31662","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223293283.pdf","grobid_xml":"https://content.openalex.org/works/W7223293283.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161102297","https://openalex.org/W7160876754","https://openalex.org/W7211923942","https://openalex.org/W7165451851","https://openalex.org/W7204924722","https://openalex.org/W7167513016","https://openalex.org/W7220912991","https://openalex.org/W7164991709","https://openalex.org/W7221532410","https://openalex.org/W7172149508"],"abstract_inverted_index":{"We":[0,102,140],"consider":[1],"online":[2,108],"monitoring":[3],"of":[4,12,31,121,129,144],"an":[5,85,107],"AI":[6,80,130],"system":[7,18],"that":[8,126,132,156,191],"produces":[9],"a":[10,20,25,53,56,64,89,137,142,154],"sequence":[11],"decisions.":[13],"At":[14],"each":[15],"round,":[16],"the":[17,29,32,44,79,94,114,119,127,163,203],"outputs":[19,63],"proposed":[21],"decision":[22,35,81],"together":[23],"with":[24,146,150],"confidence":[26,37],"score":[27,38],"estimating":[28],"trustworthiness":[30],"decision.":[33],"The":[34],"and":[36,62,96,171,187],"need":[39,204],"not":[40],"be":[41],"produced":[42],"by":[43],"same":[45],"model:":[46],"for":[47,168,205],"example,":[48],"one":[49],"agent":[50,59],"may":[51],"propose":[52],"decision,":[54],"while":[55,124,200],"separate":[57],"verifier":[58],"evaluates":[60],"it":[61,160],"correctness":[65],"or":[66,83,99],"safety":[67],"score.":[68],"Based":[69],"on":[70,176],"this":[71,104],"information,":[72],"we":[73],"must":[74],"decide":[75],"whether":[76],"to":[77,117,180,209],"accept":[78],"automatically":[82],"consult":[84],"expert,":[86],"such":[87],"as":[88,106],"human":[90,206],"auditor,":[91],"who":[92],"reviews":[93],"proposal":[95],"either":[97],"accepts":[98],"corrects":[100],"it.":[101],"formulate":[103],"task":[105],"constrained":[109],"optimization":[110],"problem":[111],"in":[112,198],"which":[113],"goal":[115],"is":[116,157],"minimize":[118],"frequency":[120],"expert":[122],"auditing":[123,166,207],"guaranteeing":[125],"fraction":[128],"errors":[131],"go":[133],"unaudited":[134],"stays":[135],"below":[136],"user-defined":[138],"threshold.":[139],"derive":[141],"family":[143],"algorithms":[145],"provable":[147],"error-control":[148],"guarantees":[149],"no":[151],"assumptions,":[152],"including":[153],"method":[155],"optimally":[158],"efficient:":[159],"asymptotically":[161],"attains":[162],"best":[164],"achievable":[165],"rate":[167],"both":[169],"adversarial":[170],"i.i.d.":[172],"data":[173,188],"streams.":[174],"Experiments":[175],"screening":[177],"harmful":[178],"requests":[179],"large":[181],"language":[182],"models,":[183],"qualitative":[184],"text":[185],"annotation,":[186],"labeling":[189],"show":[190],"our":[192],"methods":[193],"achieve":[194],"valid":[195],"error":[196],"control":[197],"practice":[199],"substantially":[201],"reducing":[202],"compared":[208],"baselines.":[210]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-24T00:00:00"}