{"id":"https://openalex.org/W7220730867","doi":"https://doi.org/10.48550/arxiv.2610.03825","title":"Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score","display_name":"Same Output, Different Gold: Measuring How Reference Choice Moves a Multilingual Benchmark Score","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7220730867","doi":"https://doi.org/10.48550/arxiv.2610.03825"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.03825","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03825","pdf_url":"https://arxiv.org/pdf/2610.03825","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.03825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136446102","display_name":"Parth Kulshreshtha","orcid":"https://orcid.org/0009-0003-9236-6180","observed_orcids":["https://orcid.org/0009-0003-9236-6180"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kulshreshtha, Parth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120694094","display_name":"Shivali Dalmia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dalmia, Shivali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040618425","display_name":"Abhishek Mukherji","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukherji, Abhishek","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":true,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.4636000096797943,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.4636000096797943,"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":0.07909999787807465,"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/T11719","display_name":"Data Quality and Management","score":0.04470000043511391,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gold-standard-annotation","display_name":"gold standard annotation","score":0.5210000276565552},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"personally identifiable information","score":0.5789999961853027},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8428999781608582},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7505999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71670001745224},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6621999740600586},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311999917030334},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C204434341","wikidata":"https://www.wikidata.org/wiki/Q357789","display_name":"Adjudication","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44530001282691956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2778058735","wikidata":"https://www.wikidata.org/wiki/Q4692253","display_name":"Aggregate data","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.03825","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03825","pdf_url":"https://arxiv.org/pdf/2610.03825","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.03825","doi":"https://doi.org/10.48550/arxiv.2610.03825","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.03825","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.03825","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03825","pdf_url":"https://arxiv.org/pdf/2610.03825","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220730867.pdf","grobid_xml":"https://content.openalex.org/works/W7220730867.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2600856987","https://openalex.org/W4296777514","https://openalex.org/W4385567454","https://openalex.org/W7160161636","https://openalex.org/W7166556608","https://openalex.org/W7203692133","https://openalex.org/W2295892333","https://openalex.org/W2232659607","https://openalex.org/W7202134312","https://openalex.org/W7214428851"],"abstract_inverted_index":{"A":[0],"benchmark":[1,31],"score":[2,70],"compares":[3],"a":[4,8,29,47,55,151],"system":[5,112],"output":[6,63,78,156],"against":[7],"reference,":[9],"and":[10,46,65,79,88,91,111,124,175],"methodological":[11],"attention":[12],"falls":[13],"almost":[14],"entirely":[15],"on":[16],"the":[17,22,41,61,67,82,95,106,148,161,178,182],"first":[18],"term.":[19],"We":[20,159],"measure":[21],"second.":[23],"The":[24,69,98,130],"retained":[25,172],"annotation":[26,173],"record":[27],"of":[28,54,154],"six-language":[30],"for":[32,76,81,121],"personally":[33],"identifiable":[34],"information":[35],"contains":[36],"two":[37,101],"independent":[38,51],"annotator":[39,141],"labellings,":[40],"aggregate":[42],"shipped":[43,149],"as":[44,104],"gold,":[45],"reviewer":[48],"gold":[49],"from":[50,170],"expert":[52],"re-annotation":[53],"sample.":[56],"Using":[57],"it,":[58],"we":[59],"hold":[60],"scored":[62],"fixed":[64],"exchange":[66],"reference.":[68],"moves":[71,103],"by":[72,92],"4.95":[73],"F1":[74],"points":[75,115],"one":[77,126,140,169],"2.00":[80],"other":[83],"(95%":[84],"CIs":[85],"[3.23,":[86],"6.27]":[87],"[0.26,":[89],"3.37]),":[90],"7.55":[93],"in":[94],"worst":[96],"language.":[97],"comparison":[99],"between":[100,109],"outputs":[102],"well:":[105],"paired":[107],"interaction":[108],"reference":[110,150],"is":[113,132],"+2.95":[114],"(CI":[116],"[+1.97,":[117],"+3.87]),":[118],"survives":[119],"correction":[120],"multiple":[122],"testing,":[123],"changes":[125],"language's":[127],"margin":[128],"outright.":[129],"cause":[131],"an":[133,155],"undocumented":[134],"aggregation":[135],"default":[136],"that":[137,177],"usually":[138],"kept":[139],"when":[142],"adjudication":[143],"did":[144],"not":[145],"fire,":[146],"making":[147],"partial":[152],"copy":[153],"being":[157],"scored.":[158],"report":[160],"resulting":[162],"reference-sensitivity":[163],"band,":[164],"show":[165],"how":[166],"to":[167],"compute":[168],"any":[171],"record,":[174],"argue":[176],"quantity":[179],"belongs":[180],"beside":[181],"score.":[183]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-07T00:00:00"}