{"id":"https://openalex.org/W7214285665","doi":"https://doi.org/10.48550/arxiv.2609.29588","title":"Confidence regions for SAFE AI compliance scores","display_name":"Confidence regions for SAFE AI compliance scores","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7214285665","doi":"https://doi.org/10.48550/arxiv.2609.29588"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29588","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29588","pdf_url":"https://arxiv.org/pdf/2609.29588","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2609.29588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152902199","display_name":"Anton Sokolov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sokolov, Anton","raw_affiliation_strings":["Tyche Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tyche Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026682492","display_name":"Paolo Giudici","orcid":"https://orcid.org/0000-0002-3493-0914","observed_orcids":["https://orcid.org/0000-0002-3493-0914"]},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giudici, Paolo","raw_affiliation_strings":["University of Pavia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pavia","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152845980","display_name":"Vasily Kolesnikov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Kolesnikov, Vasily","raw_affiliation_strings":["University of Pavia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pavia","institution_ids":["https://openalex.org/I25217355"]}]}],"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8970000147819519,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8970000147819519,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.05469999834895134,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.028200000524520874,"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-regions","display_name":"confidence regions","score":0.9279999732971191},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"uncertainty quantification","score":0.9120000004768372},{"id":"https://openalex.org/keywords/covariance-matrix-estimation","display_name":"covariance matrix estimation","score":0.5699999928474426},{"id":"https://openalex.org/keywords/explainability","display_name":"explainability","score":0.8050000071525574},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.9580000042915344},{"id":"https://openalex.org/keywords/accuracy","display_name":"accuracy","score":0.7889999747276306},{"id":"https://openalex.org/keywords/robustness-to-disturbances","display_name":"robustness to disturbances","score":0.4580000042915344},{"id":"https://openalex.org/keywords/effective-dimension","display_name":"effective dimension","score":0.3840000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4945000112056732},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C2781460075","wikidata":"https://www.wikidata.org/wiki/Q1399332","display_name":"Compliance (psychology)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32589998841285706},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27889999747276306},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.29588","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29588","pdf_url":"https://arxiv.org/pdf/2609.29588","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.29588","doi":"https://doi.org/10.48550/arxiv.2609.29588","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29588","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:2609.29588","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29588","pdf_url":"https://arxiv.org/pdf/2609.29588","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/W7214285665.pdf","grobid_xml":"https://content.openalex.org/works/W7214285665.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1992068214","https://openalex.org/W2032770461","https://openalex.org/W2106811754","https://openalex.org/W2117897510","https://openalex.org/W2150346868","https://openalex.org/W2186656473","https://openalex.org/W2328176404","https://openalex.org/W2506768821","https://openalex.org/W2602968150","https://openalex.org/W3118640283","https://openalex.org/W4234552994","https://openalex.org/W4323312052","https://openalex.org/W4375869722","https://openalex.org/W4390946269","https://openalex.org/W4402024747","https://openalex.org/W4417334604","https://openalex.org/W7125791436","https://openalex.org/W7133236347","https://openalex.org/W7147410075"],"related_works":["https://openalex.org/W7170196719","https://openalex.org/W4417334604","https://openalex.org/W4412580153","https://openalex.org/W7153468377","https://openalex.org/W4393385547","https://openalex.org/W7163738492","https://openalex.org/W7203722361","https://openalex.org/W6893192896","https://openalex.org/W7165895454","https://openalex.org/W4411357649"],"abstract_inverted_index":{"Artificial":[0],"Intelligence":[1],"trustworthiness":[2],"scores":[3],"are":[4,42,61,94],"moving":[5],"from":[6,121],"research":[7],"dashboards":[8],"into":[9,63,139],"compliance":[10,16,29,66,89,211],"claims":[11],"and":[12,31,52,118,144,155,171,190,203],"procurement":[13],"decisions.":[14],"A":[15,133],"claim":[17],"is":[18],"a":[19,32,56,64,72,97,115,218],"statistical":[20],"decision":[21],"based":[22,43],"on":[23,44,55,96,152,196],"the":[24,86,107,111,122,128,153,156,160,176,188,193,197],"comparison":[25],"between":[26],"an":[27,82,140,145],"estimated":[28,95,157],"metric":[30],"set":[33],"threshold.":[34],"The":[35,59,163,206],"recently":[36],"proposed":[37],"integrated":[38,62],"SAFE":[39,87],"AI":[40,88],"metrics":[41,60,93],"three":[45],"basic":[46],"rank-graduation":[47],"measures":[48],"of":[49,110,159,165,178,192],"accuracy,":[50],"explainability":[51],"robustness,":[53],"expressed":[54],"common":[57],"footing.":[58],"single":[65],"score,":[67],"so":[68,101],"far":[69],"reported":[70],"as":[71],"point":[73],"value.":[74],"In":[75],"this":[76],"paper":[77],"we":[78],"propose":[79],"to":[80,85,168],"add":[81],"uncertainty":[83,158,220],"layer":[84],"score.":[90],"All":[91],"component":[92,112,161],"shared":[98],"test":[99],"sample,":[100],"their":[102],"errors":[103],"covary.":[104],"We":[105],"estimate":[106],"full":[108],"covariance":[109],"vector":[113],"with":[114,149],"paired":[116],"bootstrap,":[117],"quantify":[119],"departures":[120],"source-wise":[123],"independence":[124,179],"baseline":[125],"suggested":[126],"by":[127],"integrated-metrics":[129],"framework's":[130],"variability":[131],"decomposition.":[132],"closed-form":[134],"identity":[135],"splits":[136],"such":[137],"departure":[138],"uncertainty-weighted":[141],"effective":[142],"dimension":[143],"exposure-weighted":[146],"data-driven":[147],"correlation,":[148],"both":[150,169],"depending":[151],"aggregator":[154,198],"metrics.":[162],"application":[164],"our":[166],"proposal":[167],"real":[170],"simulated":[172],"data":[173],"shows":[174],"that":[175],"assumption":[177],"can":[180,214],"either":[181],"narrow":[182],"or":[183],"widen":[184],"confidence":[185,208],"bands,":[186],"while":[187],"direction":[189],"magnitude":[191],"effect":[194],"depend":[195],"type,":[199],"machine":[200],"learning":[201],"model,":[202],"perturbation":[204],"family.":[205],"resulting":[207],"region":[209],"supports":[210],"decisions,":[212],"which":[213],"be":[215],"documented":[216],"in":[217],"formal":[219],"certificate.":[221]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-26T00:00:00"}