{"id":"https://openalex.org/W7114805484","doi":"https://doi.org/10.48550/arxiv.2512.08371","title":"A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research","display_name":"A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7114805484","doi":"https://doi.org/10.48550/arxiv.2512.08371"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.08371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.08371","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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.2512.08371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chung, Simon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung, Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vorland, Colby J.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vorland, Colby J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Maney, Donna L.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maney, Donna L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Brown, Andrew W.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brown, Andrew W.","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/T11550","display_name":"Text and Document Classification Technologies","score":0.5773000121116638,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.5773000121116638,"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/T13309","display_name":"Reliability and Agreement in Measurement","score":0.05380000174045563,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.02410000003874302,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/multivariate-statistics","display_name":"Multivariate statistics","score":0.6898000240325928},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6021000146865845},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5637000203132629},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49630001187324524},{"id":"https://openalex.org/keywords/sampling-distribution","display_name":"Sampling distribution","score":0.4918999969959259},{"id":"https://openalex.org/keywords/bernoulli-distribution","display_name":"Bernoulli distribution","score":0.48010000586509705},{"id":"https://openalex.org/keywords/multivariate-normal-distribution","display_name":"Multivariate normal distribution","score":0.47450000047683716},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.45730000734329224}],"concepts":[{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.6898000240325928},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6021000146865845},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5458999872207642},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5322999954223633},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49630001187324524},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C27956954","wikidata":"https://www.wikidata.org/wiki/Q391371","display_name":"Bernoulli distribution","level":3,"score":0.48010000586509705},{"id":"https://openalex.org/C177384507","wikidata":"https://www.wikidata.org/wiki/Q1149000","display_name":"Multivariate normal distribution","level":3,"score":0.47450000047683716},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C152361515","wikidata":"https://www.wikidata.org/wiki/Q181328","display_name":"Bernoulli's principle","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C38180746","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate analysis","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41100001335144043},{"id":"https://openalex.org/C51921466","wikidata":"https://www.wikidata.org/wiki/Q1627586","display_name":"Frequency distribution","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C67926830","wikidata":"https://www.wikidata.org/wiki/Q5051810","display_name":"Categorical distribution","level":5,"score":0.33799999952316284},{"id":"https://openalex.org/C199075045","wikidata":"https://www.wikidata.org/wiki/Q762856","display_name":"Frequency","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C82152865","wikidata":"https://www.wikidata.org/wiki/Q7208505","display_name":"Poisson sampling","level":5,"score":0.27649998664855957},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.08371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.08371","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.08371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.08371","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5942427515983582,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Datasets":[0],"may":[1],"contain":[2],"observations":[3,28],"with":[4,29,133],"multiple":[5],"labels.":[6],"If":[7],"the":[8,16,42,101,167],"labels":[9,17,31],"are":[10],"not":[11],"mutually":[12],"exclusive,":[13],"and":[14,38,91,150,154],"if":[15],"vary":[18],"greatly":[19],"in":[20,45],"frequency,":[21],"obtaining":[22],"a":[23,46,56,65,70,118,123,162],"sample":[24,124],"that":[25,74],"includes":[26],"sufficient":[27],"scarcer":[30],"to":[32,85,117,140],"make":[33],"inferences":[34],"about":[35],"those":[36],"labels,":[37],"which":[39],"deviates":[40],"from":[41,128],"population":[43],"frequencies":[44,84],"known":[47],"manner,":[48],"creates":[49],"challenges.":[50],"In":[51],"this":[52,115],"paper,":[53],"we":[54],"consider":[55],"multivariate":[57,87],"Bernoulli":[58,88],"distribution":[59,63,89,106],"as":[60],"our":[61],"underlying":[62],"of":[64,120,125,130,169],"multi-label":[66],"problem.":[67],"We":[68,113,138],"present":[69],"novel":[71],"sampling":[72,103],"algorithm":[73],"takes":[75],"label":[76,83,96,111],"dependencies":[77],"into":[78],"account.":[79],"It":[80],"uses":[81],"observed":[82],"estimate":[86],"parameters":[90],"calculates":[92],"weights":[93],"for":[94,110,156],"each":[95],"combination.":[97],"This":[98,159],"approach":[99,116,160],"ensures":[100],"weighted":[102],"acquires":[104],"target":[105],"characteristics":[107],"while":[108],"accounting":[109],"dependencies.":[112,158],"applied":[114],"variety":[119],"datasets,":[121],"including":[122],"research":[126],"articles":[127],"Web":[129],"Science":[131],"labeled":[132],"64":[134],"biomedical":[135],"topic":[136],"categories.":[137,171],"aimed":[139],"preserve":[141],"category":[142,157],"frequency":[143,146],"order,":[144],"reduce":[145],"differences":[147],"between":[148],"most":[149],"least":[151],"common":[152],"categories,":[153],"account":[155],"produced":[161],"more":[163],"balanced":[164],"sub-sample,":[165],"enhancing":[166],"representation":[168],"minority":[170]},"counts_by_year":[],"updated_date":"2026-09-11T09:22:31.653822","created_date":"2025-12-11T00:00:00"}