{"id":"https://openalex.org/W7165785310","doi":"https://doi.org/10.48550/arxiv.2606.24020","title":"You Don't Need to Run Every Eval","display_name":"You Don't Need to Run Every Eval","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165785310","doi":"https://doi.org/10.48550/arxiv.2606.24020"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.24020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24020","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":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.2606.24020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065836136","display_name":"Yuchen Zeng","orcid":"https://orcid.org/0000-0002-2766-0055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120841880","display_name":"Dimitris Papailiopoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papailiopoulos, Dimitris","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":0.33559998869895935,"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":0.33559998869895935,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.07769999653100967,"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":0.07039999961853027,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6485000252723694},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5626999735832214},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.34929999709129333},{"id":"https://openalex.org/keywords/rest","display_name":"Rest (music)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.3312999904155731},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.3190000057220459},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.31619998812675476}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6455000042915344},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5626999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C77265313","wikidata":"https://www.wikidata.org/wiki/Q879844","display_name":"Rest (music)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C98347192","wikidata":"https://www.wikidata.org/wiki/Q7705804","display_name":"Test score","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.24020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24020","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":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.2606.24020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24020","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"modern":[1],"model":[2],"release":[3,197],"reports":[4],"scores":[5,67,85,128],"on":[6,52,108,114,213],"40+":[7],"benchmarks":[8,54,71,110,153],"and":[9,27,59,96,133,204],"the":[10,29,32,88,104,109,162,198,201],"same":[11],"evaluations":[12],"were":[13],"run":[14,39],"many":[15],"more":[16],"times":[17],"before":[18],"it:":[19],"to":[20,38,129,169,193],"track":[21],"training":[22],"progress,":[23],"compare":[24],"design":[25,117],"choices,":[26],"select":[28],"checkpoint":[30],"for":[31],"release.":[33],"But":[34],"do":[35],"we":[36,116,147],"need":[37],"every":[40],"eval?":[41],"We":[42,79,196],"compile":[43],"a":[44,65,119,134,149,165,174,178,190],"public":[45,167],"score":[46,199,212],"matrix":[47,89,122],"of":[48,103,151,164],"84":[49],"frontier":[50],"models":[51,107],"133":[53,70],"(2,604":[55],"cells,":[56],"23.3%":[57],"filled)":[58],"find":[60,148],"it":[61],"is":[62],"approximately":[63],"rank-2:":[64],"model's":[66,166,191,211],"across":[68],"all":[69],"are":[72,90],"largely":[73],"determined":[74],"by":[75],"just":[76],"two":[77,83,94,97],"numbers.":[78],"confirm":[80],"this":[81],"in":[82],"ways:":[84],"hidden":[86],"from":[87],"best":[91],"recovered":[92],"using":[93],"factors,":[95],"factors":[98],"already":[99],"explain":[100],"over":[101],"90%":[102],"variation":[105],"among":[106],"they":[111],"share.":[112],"Building":[113],"this,":[115],"BenchPress:":[118],"logit-space":[120],"rank-2":[121],"completion":[123],"method":[124],"that":[125,137,159,208],"recovers":[126],"held-out":[127],"within":[130,170,194],"4.6":[131],"points,":[132],"confidence":[135],"layer":[136],"says":[138],"when":[139],"each":[140],"prediction":[141],"can":[142,160,188],"be":[143],"trusted.":[144],"Using":[145],"BenchPress,":[146],"subset":[150],"five":[152],"{GPQA-D,":[154,181],"HLE,":[155],"Codeforces,":[156],"MMLU-Pro,":[157,182],"ARC-AGI-1}":[158],"recover":[161],"rest":[163],"scorecard":[168],"3.93":[171],"points.":[172],"For":[173],"tighter":[175],"inference":[176],"budget,":[177],"cheaper":[179],"set":[180],"Aider":[183],"Polyglot,":[184],"MATH-500,":[185],"AIME":[186],"2026}":[187],"predict":[189],"evals":[192],"4.55.":[195],"matrix,":[200],"BenchPress":[202],"code,":[203],"an":[205],"interactive":[206],"tool":[207],"predicts":[209],"any":[210,214],"benchmark.":[215]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-25T00:00:00"}