{"id":"https://openalex.org/W4409051233","doi":"https://doi.org/10.1145/3722043","title":"How to Evaluate AI that's Smarter than Us","display_name":"How to Evaluate AI that's Smarter than Us","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4409051233","doi":"https://doi.org/10.1145/3722043"},"language":"en","primary_location":{"id":"doi:10.1145/3722043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3722043","pdf_url":null,"source":{"id":"https://openalex.org/S45584542","display_name":"Queue","issn_l":"1542-7730","issn":["1542-7730","1542-7749"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Queue","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116868244","display_name":"Chip Huyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chip Huyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5116868244"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03312503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"1","first_page":"39","last_page":"63"},"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":0.4805000126361847,"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":0.4805000126361847,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.4399999976158142,"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":0.4386410117149353},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37188684940338135},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33263951539993286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4386410117149353},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37188684940338135},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33263951539993286}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3722043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3722043","pdf_url":null,"source":{"id":"https://openalex.org/S45584542","display_name":"Queue","issn_l":"1542-7730","issn":["1542-7730","1542-7749"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Queue","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Evaluating":[0],"AI":[1,20,44,55,62,68],"models":[2],"that":[3],"surpass":[4],"human":[5,58],"expertise":[6],"in":[7,30,70],"the":[8,25],"task":[9],"at":[10],"hand":[11],"presents":[12],"unique":[13],"challenges.":[14],"These":[15],"challenges":[16],"only":[17],"grow":[18],"as":[19],"becomes":[21],"more":[22],"intelligent.":[23],"However,":[24],"three":[26],"effective":[27],"strategies":[28,39],"presented":[29],"this":[31],"article":[32],"exist":[33],"to":[34,60],"address":[35],"these":[36],"hurdles.":[37],"The":[38],"are:":[40],"Functional":[41],"correctness:":[42],"evaluating":[43,67],"by":[45],"how":[46],"well":[47],"it":[48],"accomplishes":[49],"its":[50],"intended":[51],"tasks;":[52],"AI-as-a-judge:":[53],"using":[54],"instead":[56,75],"of":[57,76],"experts":[59],"evaluate":[61],"outputs;":[63],"and":[64],"Comparative":[65],"evaluation:":[66],"systems":[69],"relationship":[71],"with":[72],"each":[73],"other":[74],"independently.":[77]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}