{"id":"https://openalex.org/W7224649449","doi":"https://doi.org/10.5281/zenodo.23752418","title":"Benchmark Ranking Stability: Separating Score Order from Evidence","display_name":"Benchmark Ranking Stability: Separating Score Order from Evidence","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224649449","doi":"https://doi.org/10.5281/zenodo.23752418"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23752418","doi":"https://doi.org/10.5281/zenodo.23752418","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23752418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23752418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158865149","display_name":"Pooria Arab","orcid":"https://orcid.org/0009-0005-9964-6841","observed_orcids":["https://orcid.org/0009-0005-9964-6841"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pooria Arab","raw_affiliation_strings":["Independent researcher"],"raw_orcid":"https://orcid.org/0009-0005-9964-6841","affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5158865149"],"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":0.10189999639987946,"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":0.10189999639987946,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.08980000019073486,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10991","display_name":"Game Theory and Voting Systems","score":0.05510000139474869,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/simulated-populations","display_name":"simulated populations","score":0.5820000171661377},{"id":"https://openalex.org/keywords/bootstrap-confidence-intervals","display_name":"bootstrap confidence intervals","score":0.503000020980835},{"id":"https://openalex.org/keywords/tie-breaking","display_name":"tie-breaking","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8668000102043152},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8271999955177307},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.510699987411499},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43810001015663147},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3458000123500824},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C169345407","wikidata":"https://www.wikidata.org/wiki/Q8216221","display_name":"Uncorrelated","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23752418","doi":"https://doi.org/10.5281/zenodo.23752418","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23752418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23752419","doi":"https://doi.org/10.5281/zenodo.23752419","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23752419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23752418","doi":"https://doi.org/10.5281/zenodo.23752418","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23752418","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7210269356","https://openalex.org/W7223149495","https://openalex.org/W7163992851","https://openalex.org/W6963672917","https://openalex.org/W4415131635","https://openalex.org/W2612070057","https://openalex.org/W7214801232","https://openalex.org/W2536515792","https://openalex.org/W7214792899","https://openalex.org/W4400926237"],"abstract_inverted_index":{"A":[0],"benchmark":[1],"score":[2],"orders":[3],"systems":[4],"without":[5],"showing":[6],"how":[7],"that":[8],"order":[9],"depends":[10],"on":[11],"the":[12,50,107],"evaluation":[13],"sample.":[14],"Benchmark":[15],"Ranking":[16],"Stability":[17],"combines":[18],"paired":[19],"item":[20,77],"resampling,":[21],"repeated":[22],"runs,":[23],"and":[24,61,135],"prompt-specific":[25],"ranks.":[26],"Its":[27],"public":[28],"suite":[29],"contains":[30],"60":[31],"reasoning":[32],"items":[33],"across":[34,114],"6":[35],"families,":[36],"each":[37],"with":[38,58],"5":[39],"prompts.":[40],"We":[41,53],"run":[42],"9":[43],"scripted":[44],"or":[45,142],"mock":[46],"controls":[47],"twice":[48],"through":[49],"actual":[51],"evaluator.":[52],"also":[54],"evaluate":[55],"simulated":[56,82],"populations":[57,83],"different":[59],"sizes":[60],"correctness":[62],"gaps,":[63],"using":[64],"12":[65],"seeds":[66],"per":[67],"condition.":[68],"The":[69,128],"answer-key":[70],"control":[71],"reaches":[72],"1.000":[73],"[0.940,":[74],"1.000]":[75],"all-variant":[76],"success":[78],"(Wilson":[79],"interval).":[80],"In":[81],"of":[84],"eight":[85],"agents,":[86],"a":[87,139,143],"designated":[88],"leader's":[89],"mean":[90],"bootstrap":[91],"first-place":[92],"share":[93],"changes":[94],"from":[95],"0.150":[96],"[0.090,":[97],"0.222]":[98],"at":[99,106],"equal":[100],"ability":[101],"to":[102],"0.644":[103],"[0.568,":[104],"0.728]":[105],"largest":[108],"gap.":[109],"These":[110],"are":[111],"confidence":[112],"intervals":[113],"simulation":[115],"seeds.":[116],"Exact":[117],"ties":[118],"retain":[119],"high":[120],"rank":[121],"agreement":[122],"while":[123],"offering":[124],"no":[125],"unique":[126],"winner.":[127],"contribution":[129],"is":[130],"an":[131],"inspectable":[132],"ranking":[133],"diagnostic":[134],"controlled":[136],"validation,":[137],"not":[138],"learned-model":[140],"leaderboard":[141],"new":[144],"estimator.":[145]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-30T00:00:00"}