{"id":"https://openalex.org/W7160436962","doi":"https://doi.org/10.48550/arxiv.2605.03135","title":"Instance-Level Costs for Nuanced Classifier Evaluation","display_name":"Instance-Level Costs for Nuanced Classifier Evaluation","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160436962","doi":"https://doi.org/10.48550/arxiv.2605.03135"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.03135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03135","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.03135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135468793","display_name":"Kabir Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Kabir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034715099","display_name":"Stephen Mussmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mussmann, Stephen","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15240000188350677,"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":0.15240000188350677,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.14339999854564667,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.10779999941587448,"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/word-error-rate","display_name":"Word error rate","score":0.5616000294685364},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3955000042915344},{"id":"https://openalex.org/keywords/standard-error","display_name":"Standard error","score":0.3840999901294708},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.367900013923645},{"id":"https://openalex.org/keywords/bayes-error-rate","display_name":"Bayes error rate","score":0.3407999873161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513000130653381},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43230000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C18747219","wikidata":"https://www.wikidata.org/wiki/Q620994","display_name":"Standard error","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3630000054836273},{"id":"https://openalex.org/C143809311","wikidata":"https://www.wikidata.org/wiki/Q4874458","display_name":"Bayes error rate","level":5,"score":0.3407999873161316},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C93983250","wikidata":"https://www.wikidata.org/wiki/Q795053","display_name":"Cost estimate","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C165473641","wikidata":"https://www.wikidata.org/wiki/Q3306280","display_name":"Sampling error","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.03135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03135","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.03135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03135","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7302622199058533,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Standard":[0],"classification":[1,43],"treats":[2],"all":[3],"errors":[4,24,44],"equally,":[5],"but":[6],"in":[7],"applications":[8],"such":[9],"as":[10],"content":[11],"moderation":[12],"and":[13,48,75,133],"medical":[14],"screening,":[15],"mistakes":[16,101],"on":[17,25,103],"clear-cut":[18],"cases":[19],"are":[20,56],"more":[21],"costly":[22],"than":[23,86],"ambiguous":[26],"ones.":[27],"From":[28],"a":[29,39,128],"contextual":[30],"bandit":[31],"framework,":[32],"we":[33,78],"propose":[34],"normalized":[35],"excess":[36],"cost":[37],"(NEC),":[38],"metric":[40],"that":[41,80,99,110],"weighs":[42],"by":[45],"per-example":[46],"costs":[47,55,112],"reduces":[49],"to":[50],"standard":[51],"error":[52,87,92],"rate":[53,93],"when":[54],"uniform.":[57],"Costs":[58],"can":[59,94],"derive":[60],"from":[61,66],"annotator":[62],"vote":[63],"margins,":[64],"distance":[65],"decision":[67],"thresholds,":[68],"or":[69,120],"confidence":[70],"ratings.":[71],"Across":[72],"text,":[73],"image,":[74],"tabular":[76],"benchmarks,":[77],"find":[79,109],"NEC":[81],"is":[82],"often":[83],"substantially":[84],"lower":[85],"rate:":[88],"models":[89],"with":[90],"5%":[91],"achieve":[95],"1.8%":[96],"NEC,":[97],"revealing":[98],"most":[100],"concentrate":[102],"ambiguous,":[104],"low-cost":[105],"examples.":[106],"We":[107],"also":[108],"incorporating":[111],"into":[113],"training":[114,141],"via":[115],"loss":[116],"weighting,":[117],"sampling":[118],"strategies,":[119],"regression":[121],"yields":[122],"inconsistent":[123],"benefits.":[124],"Our":[125],"framework":[126],"provides":[127],"practical":[129],"methodology":[130],"for":[131],"deriving":[132],"evaluating":[134],"instance-level":[135],"misclassification":[136],"costs,":[137],"even":[138],"if":[139],"cost-sensitive":[140],"offers":[142],"limited":[143],"benefit.":[144]},"counts_by_year":[],"updated_date":"2026-07-08T06:17:01.165560","created_date":"2026-05-07T00:00:00"}