{"id":"https://openalex.org/W1982723861","doi":"https://doi.org/10.1145/2746539.2746580","title":"Preserving Statistical Validity in Adaptive Data Analysis","display_name":"Preserving Statistical Validity in Adaptive Data Analysis","publication_year":2015,"publication_date":"2015-06-03","ids":{"openalex":"https://openalex.org/W1982723861","doi":"https://doi.org/10.1145/2746539.2746580","mag":"1982723861"},"language":"en","primary_location":{"id":"doi:10.1145/2746539.2746580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2746539.2746580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the forty-seventh annual ACM symposium on Theory of Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011820318","display_name":"Cynthia Dwork","orcid":"https://orcid.org/0000-0001-7177-3738"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cynthia Dwork","raw_affiliation_strings":["Microsoft Research, Mountain View, CA, USA","Microsoft Research, Mountain View, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Mountain View, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054675941","display_name":"Vitaly Feldman","orcid":"https://orcid.org/0000-0002-3904-759X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitaly Feldman","raw_affiliation_strings":["IBM Research, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039915143","display_name":"Moritz Hardt","orcid":"https://orcid.org/0009-0000-7694-3038"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moritz Hardt","raw_affiliation_strings":["IBM Research, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003318200","display_name":"Toniann Pitassi","orcid":"https://orcid.org/0000-0002-8668-2174"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Toniann Pitassi","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086367709","display_name":"Omer Reingold","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omer Reingold","raw_affiliation_strings":["Samsung Research, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057693522","display_name":"Aaron Roth","orcid":"https://orcid.org/0000-0002-0586-0515"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Leon Roth","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":265,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9962000250816345,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9962000250816345,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9918000102043152,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9898999929428101,"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/spurious-relationship","display_name":"Spurious relationship","score":0.7934975028038025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7266427278518677},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.6486420035362244},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.6339921951293945},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5616403222084045},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5131007432937622},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48161786794662476},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.4650828242301941},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4578406512737274},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42979440093040466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4160309433937073},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16021496057510376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14605501294136047}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7934975028038025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266427278518677},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.6486420035362244},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.6339921951293945},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5616403222084045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5131007432937622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48161786794662476},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.4650828242301941},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4578406512737274},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42979440093040466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4160309433937073},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16021496057510376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14605501294136047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2746539.2746580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2746539.2746580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the forty-seventh annual ACM symposium on Theory of Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6701009612","display_name":null,"funder_award_id":"CNS 1253345, CCF 1101389","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W27434444","https://openalex.org/W44899178","https://openalex.org/W158824538","https://openalex.org/W607505555","https://openalex.org/W1520252399","https://openalex.org/W1554944419","https://openalex.org/W1555759181","https://openalex.org/W1557833142","https://openalex.org/W1873763122","https://openalex.org/W1885924565","https://openalex.org/W1980729038","https://openalex.org/W1985310469","https://openalex.org/W1987777080","https://openalex.org/W1995692164","https://openalex.org/W1995897489","https://openalex.org/W2010523825","https://openalex.org/W2018676119","https://openalex.org/W2027595342","https://openalex.org/W2065563937","https://openalex.org/W2067833766","https://openalex.org/W2077217970","https://openalex.org/W2077641783","https://openalex.org/W2081814119","https://openalex.org/W2082233060","https://openalex.org/W2098302384","https://openalex.org/W2109722477","https://openalex.org/W2110065044","https://openalex.org/W2110868467","https://openalex.org/W2124612670","https://openalex.org/W2129428954","https://openalex.org/W2139338362","https://openalex.org/W2144981148","https://openalex.org/W2161498332","https://openalex.org/W2162341153","https://openalex.org/W2167191085","https://openalex.org/W2167567739","https://openalex.org/W2168341554","https://openalex.org/W2322006099","https://openalex.org/W2331384579","https://openalex.org/W2399077675","https://openalex.org/W2598809989","https://openalex.org/W2787894218","https://openalex.org/W2951404410","https://openalex.org/W2951851906","https://openalex.org/W2951865872","https://openalex.org/W2952304018","https://openalex.org/W2964189588","https://openalex.org/W3000680563","https://openalex.org/W3014064419","https://openalex.org/W4205228770","https://openalex.org/W4236362309","https://openalex.org/W4285719527","https://openalex.org/W6676367512","https://openalex.org/W7035933518"],"related_works":["https://openalex.org/W3121164913","https://openalex.org/W137830373","https://openalex.org/W3000984192","https://openalex.org/W2103073163","https://openalex.org/W4286952477","https://openalex.org/W2461683294","https://openalex.org/W4321348134","https://openalex.org/W4387929287","https://openalex.org/W4226211120","https://openalex.org/W1987205174"],"abstract_inverted_index":{"A":[0],"great":[1],"deal":[2],"of":[3,12,19,50,55,62,98,104],"effort":[4],"has":[5],"been":[6],"devoted":[7],"to":[8,23,64,70],"reducing":[9],"the":[10,17,29,44,48,53,76,96,102],"risk":[11],"spurious":[13],"scientific":[14],"discoveries,":[15],"from":[16],"use":[18],"sophisticated":[20],"validation":[21],"techniques,":[22],"deep":[24],"statistical":[25,56],"methods":[26],"for":[27],"controlling":[28],"false":[30],"discovery":[31],"rate":[32],"in":[33,81],"multiple":[34],"hypothesis":[35],"testing.":[36],"However,":[37],"there":[38],"is":[39,84],"a":[40,59],"fundamental":[41],"disconnect":[42],"between":[43],"theoretical":[45],"results":[46],"and":[47,86,90,101],"practice":[49,82],"data":[51,77,83,99],"analysis:":[52],"theory":[54],"inference":[57],"assumes":[58],"fixed":[60],"collection":[61],"hypotheses":[63,89],"be":[65,71],"tested,":[66],"or":[67],"learning":[68],"algorithms":[69],"applied,":[72],"selected":[73],"non-adaptively":[74],"before":[75],"are":[78],"gathered,":[79],"whereas":[80],"shared":[85],"reused":[87],"with":[88],"new":[91],"analyses":[92],"being":[93],"generated":[94],"on":[95],"basis":[97],"exploration":[100],"outcomes":[103],"previous":[105],"analyses.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}