{"id":"https://openalex.org/W7141502236","doi":"https://doi.org/10.48550/arxiv.2603.24999","title":"Efficient Detection of Bad Benchmark Items with Novel Scalability Coefficients","display_name":"Efficient Detection of Bad Benchmark Items with Novel Scalability Coefficients","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141502236","doi":"https://doi.org/10.48550/arxiv.2603.24999"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24999","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"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.2603.24999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130735044","display_name":"Michael Hardy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hardy, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130739205","display_name":"Joshua Gilbert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gilbert, Joshua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130757843","display_name":"Benjamin Domingue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Domingue, Benjamin","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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.6068000197410583,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.6068000197410583,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05810000002384186,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.036400001496076584,"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/isotonic-regression","display_name":"Isotonic regression","score":0.779699981212616},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.6014999747276306},{"id":"https://openalex.org/keywords/monotone-polygon","display_name":"Monotone polygon","score":0.592199981212616},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5827000141143799},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5680999755859375},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47209998965263367},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4422999918460846}],"concepts":[{"id":"https://openalex.org/C17418463","wikidata":"https://www.wikidata.org/wiki/Q3455874","display_name":"Isotonic regression","level":3,"score":0.779699981212616},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.6014999747276306},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5827000141143799},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4828999936580658},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42579999566078186},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C77056095","wikidata":"https://www.wikidata.org/wiki/Q543183","display_name":"Isotonic","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C64341305","wikidata":"https://www.wikidata.org/wiki/Q4919225","display_name":"Bivariate analysis","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30970001220703125},{"id":"https://openalex.org/C2779606619","wikidata":"https://www.wikidata.org/wiki/Q17092524","display_name":"Interchangeability","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C122048520","wikidata":"https://www.wikidata.org/wiki/Q2913954","display_name":"Percentile","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24999","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24999","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7836421132087708}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,57],"validity":[1],"of":[2,15,25,36,70,80,86,187,207],"assessments,":[3],"from":[4,103],"large-scale":[5,248],"AI":[6,154,208],"benchmarks":[7],"to":[8,111,242],"human":[9,163],"classrooms,":[10],"depends":[11],"on":[12,41],"the":[13,61,67,84,120,131,166,198,203,238],"quality":[14],"individual":[16],"items,":[17],"yet":[18],"modern":[19,247],"evaluation":[20,249],"instruments":[21],"often":[22],"contain":[23],"thousands":[24],"items":[26,50,102,177,245],"with":[27],"minimal":[28],"psychometric":[29],"vetting.":[30],"We":[31,117],"introduce":[32],"a":[33,77,112,184,230],"new":[34],"family":[35],"nonparametric":[37],"scalability":[38],"coefficients":[39,94],"based":[40],"interitem":[42],"isotonic":[43,63,122,168],"regression":[44],"for":[45,174],"efficiently":[46],"detecting":[47],"globally":[48],"bad":[49,176],"(e.g.,":[51],"miskeyed,":[52],"ambiguously":[53],"worded,":[54],"or":[55,109,182],"construct-misaligned).":[56],"central":[58],"contribution":[59],"is":[60,124,229],"signed":[62,121,167],"$R^2$,":[64],"which":[65],"measures":[66],"maximal":[68],"proportion":[69],"variance":[71],"in":[72,216,246],"one":[73],"item":[74,114,191,221],"explainable":[75],"by":[76],"monotone":[78,127,134,213],"function":[79],"another":[81],"while":[82],"preserving":[83],"direction":[85],"association":[87],"via":[88],"Kendall's":[89],"$\u03c4$.":[90],"Aggregating":[91],"these":[92],"pairwise":[93],"yields":[95],"item-level":[96],"scores":[97],"that":[98,119,142,234],"sharply":[99],"separate":[100],"problematic":[101],"acceptable":[104],"ones":[105],"without":[106,226],"assuming":[107],"linearity":[108],"committing":[110],"parametric":[113],"response":[115,192],"model.":[116],"show":[118,141],"$R^2$":[123,169],"extremal":[125],"among":[126],"predictors":[128],"(it":[129],"extracts":[130],"strongest":[132],"possible":[133],"signal":[135],"between":[136],"any":[137],"two":[138,162],"items)":[139],"and":[140,161,194,218],"this":[143],"optimality":[144],"property":[145],"translates":[146],"directly":[147],"into":[148],"practical":[149],"screening":[150],"power.":[151],"Across":[152],"three":[153],"benchmark":[155],"datasets":[156],"(HS":[157],"Math,":[158],"GSM8K,":[159],"MMLU)":[160],"assessment":[164],"datasets,":[165],"consistently":[170],"achieves":[171],"top-tier":[172],"AUC":[173],"ranking":[175],"above":[178],"good":[179],"ones,":[180],"outperforming":[181],"matching":[183],"comprehensive":[185],"battery":[186],"classical":[188],"test":[189],"theory,":[190,193],"dimensionality-based":[195],"diagnostics.":[196],"Crucially,":[197],"method":[199],"remains":[200],"robust":[201],"under":[202],"small-n/large-p":[204],"conditions":[205],"typical":[206],"evaluation,":[209],"requires":[210],"only":[211],"bivariate":[212],"fits":[214],"computable":[215],"seconds,":[217],"handles":[219],"mixed":[220],"types":[222],"(binary,":[223],"ordinal,":[224],"continuous)":[225],"modification.":[227],"It":[228],"lightweight,":[231],"model-agnostic":[232],"filter":[233],"can":[235],"materially":[236],"reduce":[237],"reviewer":[239],"effort":[240],"needed":[241],"find":[243],"flawed":[244],"regimes.":[250]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-28T00:00:00"}