{"id":"https://openalex.org/W7221566941","doi":"https://doi.org/10.1038/s41598-026-75767-8","title":"Adjudicator sensitivity of safety estimates in large language models for open-ended cardiovascular reasoning: a blinded multi-adjudicator benchmark study running title: adjudicator variability in LLM safety","display_name":"Adjudicator sensitivity of safety estimates in large language models for open-ended cardiovascular reasoning: a blinded multi-adjudicator benchmark study running title: adjudicator variability in LLM safety","publication_year":2026,"publication_date":"2026-10-12","ids":{"openalex":"https://openalex.org/W7221566941","doi":"https://doi.org/10.1038/s41598-026-75767-8"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-75767-8","doi":"https://doi.org/10.1038/s41598-026-75767-8","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-75767-8","pdf_url":"https://www.nature.com/articles/s41598-026-75767-8_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-75767-8_reference.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025747902","display_name":"Aykan \u00c7elik","orcid":"https://orcid.org/0000-0001-7261-8668","observed_orcids":["https://orcid.org/0000-0001-7261-8668"]},"institutions":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]},{"id":"https://openalex.org/I4210135971","display_name":"Izmir Atat\u00fcrk E\u011fitim ve Ara\u015ft\u0131rma Hastanesi","ror":"https://ror.org/03max4q92","country_code":"TR","type":"healthcare","lineage":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Aykan \u00c7elik","raw_affiliation_strings":["Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-7261-8668","affiliations":[{"raw_affiliation_string":"Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey","institution_ids":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007647213","display_name":"Tuncay K\u0131r\u0131\u015f","orcid":"https://orcid.org/0000-0001-9793-718X","observed_orcids":["https://orcid.org/0000-0001-9793-718X"]},"institutions":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]},{"id":"https://openalex.org/I4210135971","display_name":"Izmir Atat\u00fcrk E\u011fitim ve Ara\u015ft\u0131rma Hastanesi","ror":"https://ror.org/03max4q92","country_code":"TR","type":"healthcare","lineage":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tuncay Kiris","raw_affiliation_strings":["Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey","institution_ids":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091628098","display_name":"U\u011fur Kocaba\u015f","orcid":"https://orcid.org/0000-0001-9868-206X","observed_orcids":["https://orcid.org/0000-0001-9868-206X"]},"institutions":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]},{"id":"https://openalex.org/I4210135971","display_name":"Izmir Atat\u00fcrk E\u011fitim ve Ara\u015ft\u0131rma Hastanesi","ror":"https://ror.org/03max4q92","country_code":"TR","type":"healthcare","lineage":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ugur Kocabas","raw_affiliation_strings":["Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey","institution_ids":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5158428253","display_name":"Mustafa Karaca","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I250383648","display_name":"Izmir K\u00e2tip \u00c7elebi University","ror":"https://ror.org/024nx4843","country_code":"TR","type":"education","lineage":["https://openalex.org/I250383648"]},{"id":"https://openalex.org/I4210135971","display_name":"Izmir Atat\u00fcrk E\u011fitim ve Ara\u015ft\u0131rma Hastanesi","ror":"https://ror.org/03max4q92","country_code":"TR","type":"healthcare","lineage":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mustafa Karaca","raw_affiliation_strings":["Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cardiology, Medicine Faculty, Izmir Ataturk Training and Research Hospital, Katip Celebi University, Izmir, Turkey","institution_ids":["https://openalex.org/I250383648","https://openalex.org/I4210135971"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025747902"],"corresponding_institution_ids":["https://openalex.org/I250383648","https://openalex.org/I4210135971"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66833141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9539999961853027},{"id":"https://openalex.org/keywords/llm-safety","display_name":"LLM safety","score":0.5649999976158142},{"id":"https://openalex.org/keywords/llm-benchmarking","display_name":"LLM benchmarking","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7368999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6809999942779541},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6773999929428101},{"id":"https://openalex.org/C545542383","wikidata":"https://www.wikidata.org/wiki/Q2751242","display_name":"Medical emergency","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C2779328685","wikidata":"https://www.wikidata.org/wiki/Q1475557","display_name":"Patient safety","level":3,"score":0.36739999055862427},{"id":"https://openalex.org/C187155963","wikidata":"https://www.wikidata.org/wiki/Q629029","display_name":"Occupational safety and health","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3458999991416931},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C166735990","wikidata":"https://www.wikidata.org/wiki/Q1750812","display_name":"Human factors and ergonomics","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s41598-026-75767-8","doi":"https://doi.org/10.1038/s41598-026-75767-8","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-75767-8","pdf_url":"https://www.nature.com/articles/s41598-026-75767-8_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-75767-8","doi":"https://doi.org/10.1038/s41598-026-75767-8","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-75767-8","pdf_url":"https://www.nature.com/articles/s41598-026-75767-8_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8371999859809875,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221566941.pdf","grobid_xml":"https://content.openalex.org/works/W7221566941.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4391244927"],"related_works":["https://openalex.org/W7131671601","https://openalex.org/W7165845064","https://openalex.org/W7196962902","https://openalex.org/W7214115591","https://openalex.org/W4410495642","https://openalex.org/W7213029564","https://openalex.org/W4417327541","https://openalex.org/W7212028266","https://openalex.org/W7171662339","https://openalex.org/W7171650133"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"evaluated":[6,24],"for":[7,51,59],"safety-critical":[8],"clinical":[9,177],"reasoning,":[10],"but":[11,133],"safety":[12,52,168],"estimates":[13,150],"in":[14,151],"open-ended":[15,152],"tasks":[16],"may":[17],"depend":[18],"on":[19],"expert":[20],"adjudication":[21],"thresholds.":[22],"We":[23],"300":[25,71],"blinded":[26,74,92],"responses":[27,72,117],"generated":[28],"by":[29,89],"three":[30],"API-accessed":[31],"LLM":[32,154],"configurations":[33],"across":[34],"100":[35],"cardiovascular":[36,153],"scenarios.":[37],"Two":[38],"cardiologists":[39],"independently":[40,68],"scored":[41],"all":[42,60,70],"responses,":[43,61],"and":[44,80,161],"the":[45,102,122],"original":[46],"workflow":[47],"used":[48],"predefined":[49],"triggers":[50],"adjudication.":[53],"First-adjudicator":[54],"ascertainment":[55],"was":[56,108,131,136],"subsequently":[57],"completed":[58],"after":[62],"which":[63,170],"a":[64,90,95],"separate":[65],"non-author":[66],"cardiologist":[67,93],"re-adjudicated":[69],"while":[73],"to":[75],"model":[76],"identity,":[77],"reviewer":[78],"information,":[79],"prior":[81],"decisions;":[82],"53":[83],"discordant":[84],"classifications":[85],"were":[86,156],"then":[87],"assessed":[88],"third":[91],"using":[94],"majority-resolution":[96],"rule":[97],"fixed":[98],"before":[99],"receipt":[100],"of":[101],"third-adjudicator":[103],"results.":[104],"Continuous":[105],"quality-score":[106],"reliability":[107,160],"poor":[109],"(ICC":[110],"0.028).":[111],"The":[112],"first":[113],"adjudicator":[114,125],"classified":[115,126],"53/300":[116],"(17.7%)":[118],"as":[119,175],"safety-positive,":[120],"whereas":[121],"independent":[123],"second":[124],"0/300.":[127],"First\u2013second":[128],"crude":[129],"agreement":[130,135],"82.3%,":[132],"positive":[134],"0%.":[137],"Third-adjudicator":[138],"resolution":[139,163],"yielded":[140],"8/300":[141],"majority-classified":[142],"safety-relevant":[143],"errors":[144],"(2.7%,":[145],"95%":[146],"CI":[147],"1.4\u20135.2%).":[148],"Safety":[149],"benchmarks":[155],"highly":[157],"adjudicator-sensitive.":[158],"Multi-rater":[159],"transparent":[162],"procedures":[164],"should":[165,171],"accompany":[166],"numerical":[167],"estimates,":[169],"not":[172],"be":[173],"interpreted":[174],"real-world":[176],"error":[178],"prevalence.":[179]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-13T00:00:00"}
