{"id":"https://openalex.org/W4392157712","doi":"https://doi.org/10.1145/3614407.3643708","title":"Rethinking Machine Learning Benchmarks in the Context of Professional Codes of Conduct","display_name":"Rethinking Machine Learning Benchmarks in the Context of Professional Codes of Conduct","publication_year":2024,"publication_date":"2024-02-26","ids":{"openalex":"https://openalex.org/W4392157712","doi":"https://doi.org/10.1145/3614407.3643708"},"language":"en","primary_location":{"id":"doi:10.1145/3614407.3643708","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3614407.3643708","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3614407.3643708","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Symposium on Computer Science and Law","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3614407.3643708","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049073875","display_name":"Peter Henderson","orcid":"https://orcid.org/0000-0003-3938-0541"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter Henderson","raw_affiliation_strings":["Princeton University"],"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003703346","display_name":"Jieru Hu","orcid":"https://orcid.org/0009-0002-4370-0683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jieru Hu","raw_affiliation_strings":["Independent"],"affiliations":[{"raw_affiliation_string":"Independent","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Diab","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["McGill University"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049073875"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":1.8253,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86283802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9952999949455261,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9952999949455261,"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":0.9922999739646912,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9835000038146973,"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/benchmarking","display_name":"Benchmarking","score":0.8701353073120117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727442741394043},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6845760941505432},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6353424191474915},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.612715482711792},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5800447463989258},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5662033557891846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4890936017036438},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4739125967025757},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.43461477756500244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4160100817680359},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36592766642570496},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3372253179550171},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3215245008468628},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13797920942306519},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.09174266457557678},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.08484414219856262}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8701353073120117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727442741394043},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6845760941505432},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6353424191474915},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.612715482711792},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5800447463989258},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5662033557891846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4890936017036438},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4739125967025757},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.43461477756500244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4160100817680359},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36592766642570496},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3372253179550171},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3215245008468628},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13797920942306519},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.09174266457557678},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08484414219856262},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3614407.3643708","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3614407.3643708","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3614407.3643708","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Symposium on Computer Science and Law","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3614407.3643708","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3614407.3643708","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3614407.3643708","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Symposium on Computer Science and Law","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392157712.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1520056243","https://openalex.org/W1967169497","https://openalex.org/W2101946573","https://openalex.org/W2295598076","https://openalex.org/W2616194674","https://openalex.org/W2791170418","https://openalex.org/W2888230425","https://openalex.org/W2895996648","https://openalex.org/W2897042519","https://openalex.org/W3001807593","https://openalex.org/W3036677371","https://openalex.org/W3100279624","https://openalex.org/W3212368439","https://openalex.org/W4200302435","https://openalex.org/W4283810944","https://openalex.org/W4307079201","https://openalex.org/W4391831350"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W4399363378","https://openalex.org/W2803139007","https://openalex.org/W2088647418","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2151687600"],"abstract_inverted_index":{"Benchmarking":[0],"efforts":[1],"for":[2,69],"machine":[3,55,113],"learning":[4,56],"have":[5],"often":[6],"mimicked":[7],"(or":[8],"even":[9],"explicitly":[10],"used)":[11],"professional":[12,42,47,96,134],"licensing":[13],"exams":[14],"to":[15,58],"assess":[16,130],"capabilities":[17],"in":[18,41,62,90,115,173],"a":[19,35,106,149],"given":[20],"area,":[21],"focusing":[22],"primarily":[23],"on":[24,83,166],"accuracy":[25],"as":[26],"the":[27,143],"metric":[28],"of":[29,37,49,112,151,158],"choice.":[30],"However,":[31],"this":[32,102],"approach":[33],"neglects":[34],"variety":[36],"essential":[38],"skills":[39],"required":[40],"settings.":[43,117],"We":[44,118,136,161],"propose":[45],"that":[46,140,154],"codes":[48,97],"conduct":[50,105],"and":[51,74,109,126,168,178],"rules":[52],"can":[53],"guide":[54],"researchers":[57],"address":[59],"potential":[60],"gaps":[61],"benchmark":[63],"construction.":[64],"These":[65],"guidelines":[66],"frequently":[67],"account":[68],"situations":[70],"professionals":[71],"may":[72,81],"encounter":[73],"must":[75],"handle":[76],"with":[77],"care.":[78],"A":[79],"model":[80],"excel":[82],"an":[84],"exam":[85],"but":[86],"still":[87],"fall":[88],"short":[89],"critical":[91,174],"scenarios,":[92],"deemed":[93],"unacceptable":[94],"under":[95,133],"or":[98],"rules.":[99,135],"To":[100],"motivate":[101],"idea,":[103],"we":[104],"case":[107],"study":[108],"comparative":[110],"examination":[111],"translation":[114],"legal":[116,179],"point":[119],"out":[120,157],"several":[121],"areas":[122],"where":[123],"standard":[124],"deployments":[125],"benchmarks":[127],"do":[128],"not":[129],"key":[131],"requirements":[132],"suggest":[137],"further":[138],"refinements":[139],"would":[141],"bring":[142],"two":[144],"closer":[145],"together,":[146],"including":[147],"requiring":[148],"measurement":[150],"uncertainty":[152],"so":[153],"models":[155],"opt":[156],"uncertain":[159],"translations.":[160],"then":[162],"share":[163],"broader":[164],"insights":[165],"constructing":[167],"deploying":[169],"foundation":[170],"models,":[171],"particularly":[172],"domains":[175],"like":[176],"law":[177],"translation.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}