{"id":"https://openalex.org/W7221191964","doi":"https://doi.org/10.48550/arxiv.2610.11584","title":"Embedding-Bias in Conditional Independence Testing","display_name":"Embedding-Bias in Conditional Independence Testing","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7221191964","doi":"https://doi.org/10.48550/arxiv.2610.11584"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.11584","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.11584","pdf_url":"https://arxiv.org/pdf/2610.11584","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/2610.11584","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040183934","display_name":"Nikolaj Thams","orcid":"https://orcid.org/0000-0003-3961-5101","observed_orcids":["https://orcid.org/0000-0003-3961-5101"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Thams, Nikolaj","raw_affiliation_strings":["Department of Mathematical Sciences University of Copenhagen Copenhagen , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences University of Copenhagen Copenhagen , Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034145295","display_name":"Anton Rask Lundborg","orcid":"https://orcid.org/0000-0001-5565-5678","observed_orcids":["https://orcid.org/0000-0001-5565-5678"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lundborg, Anton Rask","raw_affiliation_strings":["Department of Mathematical Sciences University of Copenhagen Copenhagen , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences University of Copenhagen Copenhagen , Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I124055696"],"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.33149999380111694,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.33149999380111694,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.23669999837875366,"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":0.1527000069618225,"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":0.9950000047683716},{"id":"https://openalex.org/keywords/omitted-variable-bias","display_name":"omitted variable bias","score":0.7900000214576721},{"id":"https://openalex.org/keywords/sensitivity-parameter","display_name":"sensitivity parameter","score":0.5049999952316284},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.7910000085830688},{"id":"https://openalex.org/keywords/image-embeddings","display_name":"image embeddings","score":0.722000002861023},{"id":"https://openalex.org/keywords/language-model-embeddings","display_name":"language model embeddings","score":0.5630000233650208}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6916999816894531},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4828999936580658},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36090001463890076},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C120639","wikidata":"https://www.wikidata.org/wiki/Q7068958","display_name":"Null distribution","level":4,"score":0.2978000044822693},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C120577422","wikidata":"https://www.wikidata.org/wiki/Q843558","display_name":"Alternative hypothesis","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C103982235","wikidata":"https://www.wikidata.org/wiki/Q7309594","display_name":"Regular conditional probability","level":4,"score":0.2935999929904938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C174920663","wikidata":"https://www.wikidata.org/wiki/Q5159256","display_name":"Conditional dependence","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.11584","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.11584","pdf_url":"https://arxiv.org/pdf/2610.11584","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.2610.11584","doi":"https://doi.org/10.48550/arxiv.2610.11584","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.11584","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:2610.11584","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.11584","pdf_url":"https://arxiv.org/pdf/2610.11584","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":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221191964.pdf","grobid_xml":"https://content.openalex.org/works/W7221191964.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2790376986","https://openalex.org/W4302423442","https://openalex.org/W4412711442","https://openalex.org/W4414939355","https://openalex.org/W7127581686","https://openalex.org/W7151426930","https://openalex.org/W7206205246"],"related_works":["https://openalex.org/W4286892942","https://openalex.org/W4417465483","https://openalex.org/W6941344623","https://openalex.org/W3028249046","https://openalex.org/W2999595535","https://openalex.org/W4415087060","https://openalex.org/W3185115722","https://openalex.org/W3042860357","https://openalex.org/W2535806128","https://openalex.org/W6946265618"],"abstract_inverted_index":{"To":[0],"test":[1,27,86,156,185],"conditional":[2],"independence":[3],"of":[4,23,34,37,74,99,138,146],"$X$":[5,35],"and":[6,47,66,103,112,180],"$Y$":[7,38],"given":[8,39],"a":[9,71,83,154,159,168,194],"text":[10,181,191],"or":[11,36],"an":[12,18,125,198],"image":[13],"$Z$,":[14],"one":[15],"conditions":[16],"on":[17,70],"embedding":[19,79],"$\u03c8(Z)$":[20],"in":[21],"place":[22],"$Z$.":[24],"The":[25],"embedded":[26,211],"is":[28,32,171],"valid":[29,157],"if":[30],"$Z$":[31],"independent":[33],"$\u03c8(Z)$,":[40],"which":[41],"cannot":[42],"be":[43],"confirmed":[44],"from":[45,174],"data,":[46],"when":[48],"this":[49,64],"fails,":[50],"the":[51,55,78,89,97,121,129,132,135,139,143,163,175,183,205,210],"rejection":[52],"probability":[53],"under":[54,158,197],"null":[56,130,200],"hypothesis":[57],"can":[58],"tend":[59],"to":[60],"one.":[61],"We":[62],"study":[63],"failure,":[65],"show":[67],"that":[68,96],"focusing":[69],"specific":[72],"form":[73],"dependence":[75],"relaxes":[76],"what":[77],"must":[80],"retain.":[81],"For":[82],"residual":[84],"correlation":[85,137],"inspired":[87],"by":[88,108,193],"Generalised":[90],"Covariance":[91],"Measure,":[92],"validity":[93],"only":[94],"requires":[95],"parts":[98,141],"$\\mathbb{E}[X":[100,109],"\\mid":[101,105,110,114],"Z]$":[102,106],"$\\mathbb{E}[Y":[104,113],"missed":[107,140],"\u03c8(Z)]$":[111,115],"are":[116],"uncorrelated.":[117],"Otherwise,":[118],"we":[119],"treat":[120],"discarded":[122],"information":[123],"as":[124],"omitted":[126],"variable.":[127],"Under":[128],"hypothesis,":[131,201],"bias":[133],"equals":[134],"absolute":[136],"times":[142],"geometric":[144,164],"mean":[145],"two":[147],"partial":[148],"$R^2$":[149],"values.":[150],"This":[151],"identity":[152],"yields":[153],"robust":[155,184],"declared":[160],"tolerance":[161],"for":[162],"mean,":[165],"which,":[166],"like":[167],"sensitivity":[169],"parameter,":[170],"not":[172],"identified":[173],"data.":[176],"On":[177,190],"synthetic":[178],"data":[179],"embeddings,":[182],"holds":[186],"its":[187],"level":[188],"approximately.":[189],"generated":[192],"language":[195],"model,":[196],"exact":[199],"every":[202],"embedding,":[203],"even":[204],"generator's":[206],"own":[207],"states,":[208],"biases":[209],"test.":[212]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-10T00:00:00"}