{"id":"https://openalex.org/W4387963810","doi":"https://doi.org/10.1145/3769688","title":"Evaluating General-Purpose AI with Psychometrics","display_name":"Evaluating General-Purpose AI with Psychometrics","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W4387963810","doi":"https://doi.org/10.1145/3769688"},"language":"en","primary_location":{"id":"doi:10.1145/3769688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769688","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3769688","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiting Wang","orcid":"https://orcid.org/0000-0001-5768-1095"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210132158","display_name":"Annoroad Gene Technology (China)","ror":"https://ror.org/03gyd9q58","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132158"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]},{"id":"https://openalex.org/I82333064","display_name":"Chinese Academy of Governance","ror":"https://ror.org/006cgkx15","country_code":"CN","type":"government","lineage":["https://openalex.org/I82333064"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiting Wang","raw_affiliation_strings":["Beijing Key Laboratory of Research on Large Models and Intelligent Governance, Beijing, Beijing, China","Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE, Beijing, Beijing, China","Renmin University of China, Gaoling School of Artificial Intelligence, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5768-1095","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Research on Large Models and Intelligent Governance, Beijing, Beijing, China","institution_ids":["https://openalex.org/I82333064"]},{"raw_affiliation_string":"Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210132158"]},{"raw_affiliation_string":"Renmin University of China, Gaoling School of Artificial Intelligence, Beijing, Beijing, China","institution_ids":["https://openalex.org/I78988378","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liming Jiang","orcid":"https://orcid.org/0000-0001-6464-2326"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Jiang","raw_affiliation_strings":["Beijing Normal University, Beijing, Beijing, China","Microsoft Research Asia, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6464-2326","affiliations":[{"raw_affiliation_string":"Beijing Normal University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I25254941"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029864546","display_name":"Jos\u00e9 Hern\u00e1ndez\u2010Orallo","orcid":"https://orcid.org/0000-0001-9746-7632"},"institutions":[{"id":"https://openalex.org/I2802641067","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802641067"]},{"id":"https://openalex.org/I2802828525","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21","country_code":"ES","type":"government","lineage":["https://openalex.org/I2802828525"]},{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Hern\u00e1ndez-Orallo","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Comunitat Valenciana, Spain","University of Cambridge, Leverhulme Centre for the Future of Intelligence, Cambridge, Cambridgeshire, United Kingdom","ValgrAI, Valencia, Comunitat Valenciana, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9746-7632","affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Comunitat Valenciana, Spain","institution_ids":["https://openalex.org/I60053951"]},{"raw_affiliation_string":"University of Cambridge, Leverhulme Centre for the Future of Intelligence, Cambridge, Cambridgeshire, United Kingdom","institution_ids":["https://openalex.org/I2802641067"]},{"raw_affiliation_string":"ValgrAI, Valencia, Comunitat Valenciana, Spain","institution_ids":["https://openalex.org/I2802828525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004868515","display_name":"David Stillwell","orcid":"https://orcid.org/0000-0003-0174-3212"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Stillwell","raw_affiliation_strings":["University of Cambridge, Cambridge, Cambridgeshire, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0003-0174-3212","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, Cambridgeshire, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiqiang Chen","orcid":"https://orcid.org/0009-0007-2991-8447"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqiang Chen","raw_affiliation_strings":["Renmin University of China, Gaoling School of Artificial Intelligence, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2991-8447","affiliations":[{"raw_affiliation_string":"Renmin University of China, Gaoling School of Artificial Intelligence, Beijing, Beijing, China","institution_ids":["https://openalex.org/I78988378","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Luning Sun","orcid":"https://orcid.org/0000-0002-2470-4278"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luning Sun","raw_affiliation_strings":["University of Cambridge, Cambridge, Cambridgeshire, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-2470-4278","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, Cambridgeshire, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fang Luo","orcid":"https://orcid.org/0000-0003-3281-9574"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Luo","raw_affiliation_strings":["Beijing Normal University, Faculty of Psychology, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3281-9574","affiliations":[{"raw_affiliation_string":"Beijing Normal University, Faculty of Psychology, Beijing, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101255352","display_name":"Xing Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3257-3077","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210132158","https://openalex.org/I78988378","https://openalex.org/I82333064"],"apc_list":null,"apc_paid":null,"fwci":32.0212,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98010328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"69","issue":"5","first_page":"92","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8901000022888184,"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":0.8901000022888184,"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/computer-science","display_name":"Computer science","score":0.6633291244506836},{"id":"https://openalex.org/keywords/psychometrics","display_name":"Psychometrics","score":0.6505112648010254},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6413620710372925},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6001565456390381},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5964317321777344},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45574143528938293},{"id":"https://openalex.org/keywords/construct-validity","display_name":"Construct validity","score":0.45161983370780945},{"id":"https://openalex.org/keywords/management-science","display_name":"Management science","score":0.3812492787837982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32679283618927},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23830294609069824},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.14562693238258362},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07738146185874939},{"id":"https://openalex.org/keywords/developmental-psychology","display_name":"Developmental psychology","score":0.07127943634986877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6633291244506836},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.6505112648010254},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6413620710372925},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6001565456390381},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5964317321777344},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45574143528938293},{"id":"https://openalex.org/C49453240","wikidata":"https://www.wikidata.org/wiki/Q1592163","display_name":"Construct validity","level":3,"score":0.45161983370780945},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3812492787837982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32679283618927},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23830294609069824},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.14562693238258362},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07738146185874939},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.07127943634986877},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3769688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769688","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2310.16379","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.16379","pdf_url":"https://arxiv.org/pdf/2310.16379","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"pmh:doi:10.17863/cam.121669","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2310.16379","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.16379","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3769688","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769688","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1411269697","display_name":null,"funder_award_id":"CIPROM/2022/6","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"},{"id":"https://openalex.org/G1422035950","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320321864","funder_display_name":"Generalitat Valenciana"},{"id":"https://openalex.org/G1622782223","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3492592289","display_name":null,"funder_award_id":"PID2021-122830OB-C42","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G387506447","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G451917667","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G4909719005","display_name":null,"funder_award_id":"PID2021-122830OB-C42","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5967599077","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6298273575","display_name":null,"funder_award_id":"RTI2018","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7359725691","display_name":null,"funder_award_id":"62377003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7535663061","display_name":null,"funder_award_id":"AEI/10.","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321864","display_name":"Generalitat Valenciana","ror":"https://ror.org/0097mvx21"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4380136770","https://openalex.org/W2067674665","https://openalex.org/W4380568662","https://openalex.org/W3135512811","https://openalex.org/W2279151839","https://openalex.org/W2964200250","https://openalex.org/W2016749656","https://openalex.org/W2906877784","https://openalex.org/W2019962676","https://openalex.org/W2016506764"],"abstract_inverted_index":{"Rigorous":[0],"evaluation":[1,27,109,144],"of":[2,16,22,54,76,103,118,169],"general-purpose":[3],"AI":[4,89,108,173],"systems":[5],"such":[6],"as":[7,79],"large":[8],"language":[9],"models":[10],"should":[11],"allow":[12],"for":[13,44,82,166],"deepened":[14],"understanding":[15],"their":[17,23,63],"capabilities":[18],"and":[19,50,65,84,124,129,141,158],"effective":[20],"mitigation":[21],"risks.":[24],"The":[25],"current":[26],"paradigm,":[28],"mostly":[29],"reliant":[30],"on":[31,35,47],"benchmarks":[32,58],"aggregating":[33],"scores":[34],"one":[36],"or":[37],"more":[38],"tasks,":[39],"lacks":[40],"the":[41,52,74,100,152,167],"scientific":[42],"machinery":[43],"predicting":[45],"performance":[46,90],"unforeseen":[48],"tasks":[49],"explaining":[51],"variability":[53],"results.":[55],"Moreover,":[56],"existing":[57],"raise":[59,95],"growing":[60],"concerns":[61],"about":[62],"reliability":[64],"validity.":[66],"To":[67,94],"tackle":[68],"these":[69],"challenges,":[70],"we":[71,97,114,135,154],"vindicate":[72],"psychometrics,":[73],"science":[75],"psychological":[77],"measurement,":[78],"a":[80,137],"methodology":[81],"identifying":[83],"measuring":[85],"constructs":[86],"that":[87,161],"underlie":[88],"across":[91],"multiple":[92],"tasks.":[93],"awareness,":[96],"first":[98],"identify":[99],"key":[101],"advantages":[102],"adapting":[104],"psychometric":[105,119,139],"principles":[106],"to":[107,131],"through":[110],"concrete":[111],"examples;":[112],"second,":[113],"distinguish":[115],"sound":[116],"applications":[117],"techniques":[120],"from":[121],"oversimplified":[122],"ones":[123],"warn":[125],"against":[126],"common":[127],"pitfalls;":[128],"third,":[130],"encourage":[132],"general":[133],"use,":[134],"introduce":[136],"systematic":[138],"framework":[140],"an":[142],"operational":[143],"pipeline,":[145],"which":[146],"provide":[147],"practical":[148],"implementation":[149],"guidance.":[150],"In":[151],"end,":[153],"discuss":[155],"underexplored":[156],"avenues":[157],"societal":[159],"implications":[160],"open":[162],"new":[163],"research":[164],"directions":[165],"use":[168],"psychometrics":[170],"in":[171],"broader":[172],"research.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
