{"id":"https://openalex.org/W7127089587","doi":"https://doi.org/10.48550/arxiv.2601.23124","title":"Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees","display_name":"Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127089587","doi":"https://doi.org/10.48550/arxiv.2601.23124"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.23124","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.23124","pdf_url":"https://arxiv.org/pdf/2601.23124","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":"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/2601.23124","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116082920","display_name":"Angel Reyero Lobo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reyero-Lobo, Angel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026762833","display_name":"Bertrand Thirion","orcid":"https://orcid.org/0000-0001-5018-7895","observed_orcids":["https://orcid.org/0000-0001-5018-7895"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thirion, Bertrand","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay , Inria , CEA , Palaiseau , 91120 , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay , Inria , CEA , Palaiseau , 91120 , France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2738703131","https://openalex.org/I277688954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071356919","display_name":"Pierre Neuvial","orcid":"https://orcid.org/0000-0003-3584-9998","observed_orcids":["https://orcid.org/0000-0003-3584-9998"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I196454796","display_name":"Institut National des Sciences Appliqu\u00e9es de Toulouse","ror":"https://ror.org/01h8pf755","country_code":"FR","type":"education","lineage":["https://openalex.org/I196454796"]},{"id":"https://openalex.org/I4210098964","display_name":"Toulouse Mathematics Institute","ror":null,"country_code":"FR","type":null,"lineage":["https://openalex.org/I4210098964"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Neuvial, Pierre","raw_affiliation_strings":["Univ Toulouse , INSA Toulouse , CNRS , IMT , Toulouse , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ Toulouse , INSA Toulouse , CNRS , IMT , Toulouse , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I196454796","https://openalex.org/I4210098964"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9965999722480774,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9965999722480774,"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":0.0006000000284984708,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.0003000000142492354,"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/conditional-independence-tests","display_name":"conditional independence testing","score":0.996999979019165},{"id":"https://openalex.org/keywords/counterfeit-goods","display_name":"counterfeit goods","score":0.5879999995231628},{"id":"https://openalex.org/keywords/finite-sample-guarantees","display_name":"finite-sample guarantees","score":0.7250000238418579},{"id":"https://openalex.org/keywords/false-discovery-rate-control","display_name":"false discovery rate control","score":0.9599999785423279},{"id":"https://openalex.org/keywords/high-dimensional-inference","display_name":"high-dimensional inference","score":0.6729999780654907},{"id":"https://openalex.org/keywords/conditional-expectation","display_name":"conditional expectation","score":0.5649999976158142},{"id":"https://openalex.org/keywords/double-robustness","display_name":"double robustness","score":0.7009999752044678},{"id":"https://openalex.org/keywords/regularized-models","display_name":"regularized models","score":0.7910000085830688},{"id":"https://openalex.org/keywords/spurious-correlations","display_name":"spurious correlations","score":0.4059999883174896},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.531000018119812}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7333999872207642},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5891000032424927},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.4652999937534332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45820000767707825},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29490000009536743},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.29409998655319214},{"id":"https://openalex.org/C113644684","wikidata":"https://www.wikidata.org/wiki/Q1356717","display_name":"Statistical process control","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2601.23124","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.23124","pdf_url":"https://arxiv.org/pdf/2601.23124","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05681965v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05681965v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICML 2026 - 43 rd International Conference on Machine Learning, Jul 2026, Seoul, South Korea","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2601.23124","doi":"https://doi.org/10.48550/arxiv.2601.23124","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.23124","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:2601.23124","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.23124","pdf_url":"https://arxiv.org/pdf/2601.23124","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3012191354","display_name":null,"funder_award_id":"101058516","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G5065911115","display_name":"Explainable AI through Variable Importance Tests","funder_award_id":"ANR-23-CE23-0016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5241709497","display_name":null,"funder_award_id":"101058516","funder_id":"https://openalex.org/F4320338338","funder_display_name":"H2020 Research Infrastructures"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338338","display_name":"H2020 Research Infrastructures","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127089587.pdf","grobid_xml":"https://content.openalex.org/works/W7127089587.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2935780604","https://openalex.org/W7131429887","https://openalex.org/W3185155209","https://openalex.org/W3024144669","https://openalex.org/W7165137929","https://openalex.org/W4392019626","https://openalex.org/W4417465483","https://openalex.org/W3092028542","https://openalex.org/W4382202781","https://openalex.org/W7168407106"],"abstract_inverted_index":{"Conditional":[0],"independence":[1],"testing":[2],"(CIT)":[3],"is":[4],"essential":[5],"for":[6,70,89,101,123],"reliable":[7],"scientific":[8],"discovery.":[9],"It":[10],"prevents":[11],"spurious":[12],"findings":[13],"and":[14,60,64,98,131],"enables":[15],"controlled":[16],"feature":[17,130],"selection.":[18],"Recent":[19],"CIT":[20,49],"methods":[21,74],"have":[22],"used":[23],"machine":[24,102],"learning":[25,103],"(ML)":[26],"models":[27,125],"as":[28],"surrogates":[29],"of":[30,118],"the":[31,78,94,133],"underlying":[32],"distribution.":[33],"However,":[34],"model-agnostic":[35],"approaches":[36],"require":[37,86],"a":[38,48,128],"train-test":[39],"split,":[40,59],"which":[41],"reduces":[42],"statistical":[43],"power.":[44],"We":[45],"introduce":[46],"Semi-knockoffs,":[47],"method":[50],"that":[51,75],"can":[52],"accommodate":[53],"any":[54],"pre-trained":[55],"model,":[56],"avoids":[57],"this":[58],"provides":[61],"valid":[62],"p-values":[63],"false":[65],"discovery":[66],"rate":[67],"(FDR)":[68],"control":[69],"high-dimensional":[71],"settings.":[72],"Unlike":[73],"rely":[76],"on":[77],"model-$X$":[79],"assumption":[80],"(known":[81],"input":[82],"distribution),":[83],"Semi-knockoffs":[84],"only":[85],"conditional":[87],"expectations":[88],"continuous":[90],"variables.":[91],"This":[92],"makes":[93],"procedure":[95],"less":[96],"restrictive":[97],"more":[99],"practical":[100],"integration.":[104],"To":[105],"ensure":[106],"validity":[107],"when":[108],"estimating":[109],"these":[110],"expectations,":[111],"we":[112],"present":[113],"two":[114],"new":[115],"theoretical":[116],"results":[117],"independent":[119],"interest:":[120],"(i)":[121],"stability":[122],"regularized":[124],"trained":[126],"with":[127],"null":[129],"(ii)":[132],"double-robustness":[134],"property.":[135]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-02-03T00:00:00"}