{"id":"https://openalex.org/W7220929444","doi":"https://doi.org/10.48550/arxiv.2610.09601","title":"Cluster-Robust Prediction-Powered Inference","display_name":"Cluster-Robust Prediction-Powered Inference","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220929444","doi":"https://doi.org/10.48550/arxiv.2610.09601"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09601","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09601","pdf_url":"https://arxiv.org/pdf/2610.09601","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106657157","display_name":"David Broska","orcid":"https://orcid.org/0000-0002-5176-1163","observed_orcids":["https://orcid.org/0000-0002-5176-1163"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Broska, David","raw_affiliation_strings":["Department of Sociology Department of Statistics Stanford University Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Sociology Department of Statistics Stanford University Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106657158","display_name":"Michael Howes","orcid":"https://orcid.org/0009-0007-8048-3397","observed_orcids":["https://orcid.org/0009-0007-8048-3397"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howes, Michael","raw_affiliation_strings":["Department of Sociology Department of Statistics Stanford University Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Sociology Department of Statistics Stanford University Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T13030","display_name":"Survey Sampling and Estimation Techniques","score":0.28610000014305115,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13030","display_name":"Survey Sampling and Estimation Techniques","score":0.28610000014305115,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.24150000512599945,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.09830000251531601,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prediction-powered-inference","display_name":"prediction-powered inference","score":0.9990000128746033},{"id":"https://openalex.org/keywords/cluster-robust-inference","display_name":"cluster-robust inference","score":0.8370000123977661},{"id":"https://openalex.org/keywords/clustered-data","display_name":"clustered data","score":0.42399999499320984},{"id":"https://openalex.org/keywords/confidence-interval-coverage","display_name":"confidence interval coverage","score":0.6349999904632568},{"id":"https://openalex.org/keywords/standard-errors","display_name":"standard errors","score":0.6610000133514404},{"id":"https://openalex.org/keywords/asymptotic-validity","display_name":"asymptotic validity","score":0.5070000290870667},{"id":"https://openalex.org/keywords/television-news","display_name":"television news","score":0.5130000114440918}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5250999927520752},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36059999465942383},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C13662513","wikidata":"https://www.wikidata.org/wiki/Q5160087","display_name":"Confidence distribution","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.27959999442100525},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2685999870300293}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09601","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09601","pdf_url":"https://arxiv.org/pdf/2610.09601","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.2610.09601","doi":"https://doi.org/10.48550/arxiv.2610.09601","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09601","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:2610.09601","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09601","pdf_url":"https://arxiv.org/pdf/2610.09601","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/W7220929444.pdf","grobid_xml":"https://content.openalex.org/works/W7220929444.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4388327685","https://openalex.org/W4407012644","https://openalex.org/W7130415382","https://openalex.org/W7135207085","https://openalex.org/W7139967264","https://openalex.org/W7140162978","https://openalex.org/W7148712671"],"related_works":["https://openalex.org/W4388327685","https://openalex.org/W4414922473","https://openalex.org/W7126027345","https://openalex.org/W7166700504","https://openalex.org/W7151970660","https://openalex.org/W4414588259","https://openalex.org/W7139967264","https://openalex.org/W7128741866","https://openalex.org/W4407186341","https://openalex.org/W7164006983"],"abstract_inverted_index":{"Data":[0],"collection":[1],"is":[2,94],"often":[3,59],"costly":[4],"or":[5,89],"logistically":[6],"demanding,":[7],"limiting":[8],"both":[9,108],"the":[10,27,55,123,136],"questions":[11],"researchers":[12],"can":[13,19,25,49,167],"pursue":[14],"and":[15,75,110,139],"how":[16,131],"precisely":[17],"they":[18],"answer":[20],"them.":[21],"Prediction-powered":[22],"inference":[23],"(PPI)":[24],"reduce":[26],"amount":[28],"of":[29,126],"data":[30,39],"needed":[31],"for":[32],"precise":[33],"parameter":[34,57],"estimation":[35],"by":[36],"combining":[37],"labeled":[38,98,109,120],"with":[40],"machine":[41],"learning":[42],"predictions.":[43],"However,":[44],"ignoring":[45],"dependence":[46,82],"within":[47,83,117],"clusters":[48,106,121],"produce":[50],"confidence":[51,78,158],"intervals":[52,79,159],"that":[53,146],"cover":[54],"true":[56],"less":[58],"than":[60],"their":[61],"nominal":[62,169],"rate.":[63],"We":[64,128],"introduce":[65],"Cluster-Robust":[66,165],"PPI++,":[67],"which":[68,105],"provides":[69],"standard":[70,156],"errors":[71],"in":[72,104],"closed":[73],"form":[74],"asymptotically":[76],"valid":[77],"under":[80],"arbitrary":[81],"independent":[84],"clusters,":[85,99,118],"requiring":[86],"no":[87],"bootstrap":[88],"resampling.":[90],"Our":[91],"central":[92],"contribution":[93],"to":[95,153],"accommodate":[96],"partially":[97,119],"a":[100,141],"common":[101],"empirical":[102],"setting":[103],"contain":[107],"unlabeled":[111],"units.":[112],"As":[113],"units":[114],"are":[115],"dependent":[116],"violate":[122],"independence":[124],"assumption":[125],"PPI++.":[127],"also":[129],"show":[130],"precision":[132],"increases":[133],"depend":[134],"on":[135],"labeling":[137],"design,":[138],"derive":[140],"cluster-aware":[142],"power":[143],"tuning":[144],"rule":[145],"minimizes":[147],"asymptotic":[148],"variance.":[149],"In":[150],"an":[151],"application":[152],"television":[154],"news,":[155],"PPI++":[157,166],"have":[160],"coverage":[161],"below":[162],"60%,":[163],"whereas":[164],"achieve":[168],"95%":[170],"coverage.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}