{"id":"https://openalex.org/W7224769423","doi":"https://doi.org/10.5281/zenodo.23808444","title":"MedGauge: A Metrological Framework for Measuring Medical AI Agents by Program-Graded Work Products","display_name":"MedGauge: A Metrological Framework for Measuring Medical AI Agents by Program-Graded Work Products","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224769423","doi":"https://doi.org/10.5281/zenodo.23808444"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23808444","doi":"https://doi.org/10.5281/zenodo.23808444","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23808444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139759183","display_name":"Chuanjiang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chuanjiang","raw_affiliation_strings":["MedGauge Initiative"],"raw_orcid":"https://orcid.org/0009-0003-8604-3369","affiliations":[{"raw_affiliation_string":"MedGauge Initiative","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160229016","display_name":"Xiaofeng Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaofeng","raw_affiliation_strings":["MedGauge Initiative"],"raw_orcid":"https://orcid.org/0009-0002-1293-6298","affiliations":[{"raw_affiliation_string":"MedGauge Initiative","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135597165","display_name":"Haoran Zhou","orcid":"https://orcid.org/0009-0008-0854-0198","observed_orcids":["https://orcid.org/0009-0008-0854-0198"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Haoran","raw_affiliation_strings":["MedGauge Initiative"],"raw_orcid":"https://orcid.org/0009-0005-2010-9796","affiliations":[{"raw_affiliation_string":"MedGauge Initiative","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160238170","display_name":"Nian Zhen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen, Nian","raw_affiliation_strings":["MedGauge Initiative"],"raw_orcid":"https://orcid.org/0009-0000-6806-1262","affiliations":[{"raw_affiliation_string":"MedGauge Initiative","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160221399","display_name":"MedGauge Initiative","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MedGauge Initiative","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76617966,"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":0.8618000149726868,"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":0.8618000149726868,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.02160000056028366,"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"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.00930000003427267,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metrology","display_name":"metrology","score":0.5320000052452087},{"id":"https://openalex.org/keywords/human-ai-comparison","display_name":"human-AI comparison","score":0.5559999942779541},{"id":"https://openalex.org/keywords/task-typology","display_name":"task typology","score":0.6660000085830688},{"id":"https://openalex.org/keywords/attribute-sampling","display_name":"attribute sampling","score":0.7260000109672546},{"id":"https://openalex.org/keywords/uncertainty-budget","display_name":"uncertainty budget","score":0.5870000123977661},{"id":"https://openalex.org/keywords/traceability","display_name":"traceability","score":0.6620000004768372},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.39399999380111694},{"id":"https://openalex.org/keywords/evaluation-methodology","display_name":"evaluation methodology","score":0.42399999499320984},{"id":"https://openalex.org/keywords/multiplicity-control","display_name":"multiplicity control","score":0.7549999952316284}],"concepts":[{"id":"https://openalex.org/C2776548248","wikidata":"https://www.wikidata.org/wiki/Q12621536","display_name":"Judgement","level":2,"score":0.7522000074386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5508999824523926},{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C2779547435","wikidata":"https://www.wikidata.org/wiki/Q1121492","display_name":"Directive","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29820001125335693},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25279998779296875},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C195766429","wikidata":"https://www.wikidata.org/wiki/Q394","display_name":"Metrology","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23808444","doi":"https://doi.org/10.5281/zenodo.23808444","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},{"id":"doi:10.5281/zenodo.23808445","doi":"https://doi.org/10.5281/zenodo.23808445","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23808444","doi":"https://doi.org/10.5281/zenodo.23808444","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23808444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"sustainable_development_goals":[{"score":0.4043000042438507,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7224879453","https://openalex.org/W7171510721","https://openalex.org/W4402224992","https://openalex.org/W4401500550","https://openalex.org/W7203557834","https://openalex.org/W2305573925","https://openalex.org/W2989030375","https://openalex.org/W7172208487","https://openalex.org/W7104293672","https://openalex.org/W4406228877"],"abstract_inverted_index":{"Evaluation":[0],"of":[1,11,16,35,73,103,123,133,168,191,203,223,227,303,332,400,422],"medical":[2],"AI":[3],"has":[4,432],"inherited":[5],"its":[6,113,351,385],"instruments":[7,37],"from":[8,93,117,231,380],"the":[9,24,40,61,68,71,74,82,87,97,134,138,144,184,217,220,225,301,333,374,378,398,420,424],"evaluation":[10],"people:":[12],"examinations,":[13],"expert":[14],"judgement":[15,202],"free":[17,204],"text,":[18],"and":[19,55,99,136,147,199,252,256,264,273,277,326,339,371,394,397,439],"task":[20,275,291,348,360,395],"value":[21],"denominated":[22],"in":[23,283,293],"hours":[25],"a":[26,44,51,57,115,166,173,176,189,232,235,241,285,304,307,346,356,368,381,407],"practitioner":[27],"would":[28],"need.":[29],"This":[30],"working":[31],"paper":[32,344,414],"asks":[33],"which":[34,80,284],"those":[36,401],"survive":[38],"when":[39],"thing":[41],"measured":[42],"is":[43,67,81,119,150,186,427,442],"silicon":[45,90,104],"producer":[46],"(a":[47],"model":[48],"running":[49],"inside":[50],"harness":[52],"with":[53,112,259,297,314,322,350],"tools)":[54],"builds":[56,216],"measurement":[58,271,417],"framework":[59],"for":[60,70,121,137,249,377,391],"parts":[62],"that":[63,89,106,154,213],"do":[64,209],"not.":[65],"It":[66,85,152,245],"argument":[69],"construction":[72,132],"MedGauge":[75],"Methodology,":[76],"version":[77],"0.1.0":[78,331],"(https://medgauge.org/methodology/text/),":[79],"normative":[83],"text.":[84],"tests":[86],"claim":[88],"producers":[91,95,105],"differ":[92],"human":[94,145,161,177,201],"against":[96],"literature":[98,352],"finds":[100],"twelve":[101],"properties":[102],"bear":[107],"on":[108,160,175,200,312],"measurement,":[109],"each":[110,228],"stated":[111],"counter-evidence;":[114],"difference":[116,149],"people":[118],"supported":[120],"two":[122,197],"them":[124,268],"by":[125,131,196],"an":[126,280,363],"opened":[127],"source,":[128],"three":[129,295],"hold":[130],"subject,":[135],"remaining":[139],"seven":[140],"no":[141,148,298,327,336,341,416,429,435],"source":[142,387],"states":[143],"side":[146],"asserted.":[151],"shows":[153],"human-anchored":[155],"evaluations":[156],"divide":[157],"into":[158,188],"anchors":[159],"time":[162],"(which":[163,181,208],"transfer":[164,182],"as":[165,172,318,406,411],"predictor":[167],"difficulty":[169],"but":[170,366],"not":[171,210,367,410],"unit),":[174],"product":[178,185],"or":[179,206],"rule":[180],"once":[183],"converted":[187],"key":[190],"field":[192],"checks":[193],"set":[194,361,404],"independently":[195],"experts)":[198],"text":[205],"preference":[207],"transfer).":[211],"On":[212],"basis":[214],"it":[215],"measurement:":[218],"following":[219],"international":[221],"vocabulary":[222],"metrology,":[224],"reference":[226],"quantity":[229],"moves":[230],"unit":[233],"to":[234,240,384],"versioned":[236],"grading":[237],"program":[238],"applied":[239],"fixed":[242],"artifact":[243],"contract.":[244],"gives":[246],"scale":[247,261],"rules":[248],"labels,":[250],"levels":[251],"counts;":[253],"proposes":[254,345],"base":[255],"derived":[257],"quantities":[258],"their":[260],"type,":[262],"traceability":[263],"cross-harness":[265],"comparability;":[266],"maps":[267],"onto":[269],"ten":[270,274],"dimensions":[272],"labels;":[276],"sets":[278,335,372],"out":[279,373,405],"examination":[281],"regime":[282,365],"subject":[286],"passes":[287,292],"only":[288],"if":[289],"every":[290,440],"all":[294],"runs":[296],"safety":[299],"veto,":[300],"strength":[302],"pass":[305],"being":[306],"one-sided":[308],"95%":[309],"lower":[310],"bound":[311],"reliability,":[313],"execution":[315],"errors":[316],"counted":[317],"failures,":[319],"paired":[320],"comparison":[321],"step-down":[323],"multiplicity":[324],"control,":[325],"overall":[328],"score.":[329],"Version":[330],"methodology":[334],"level":[337],"threshold":[338],"issues":[340],"level.":[342],"The":[343,413],"four-layer":[347],"typology":[349],"base,":[353],"explains":[354],"why":[355],"closed,":[357],"uncalibrated,":[358],"generated":[359],"licenses":[362],"attribute-sampling":[364],"response-model":[369],"regime,":[370],"uncertainty":[375],"budget":[376],"chain":[379],"published":[382],"score":[383],"public":[386,425],"clause.":[388],"Standardised":[389],"semantics":[390],"products,":[392],"scenarios":[393],"types,":[396],"validation":[399],"standards,":[402],"are":[403],"research":[408],"plan,":[409],"results.":[412],"reports":[415],"result.":[418],"At":[419],"date":[421],"publication":[423],"site":[426],"live,":[428],"benchmark":[430],"round":[431],"been":[433],"run,":[434],"result":[436],"record":[437],"exists":[438],"leaderboard":[441],"empty.":[443]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-10-31T00:00:00"}
