{"id":"https://openalex.org/W7220728678","doi":"https://doi.org/10.48550/arxiv.2610.04559","title":"Coupling Noisy Pairwise Knowledge to the DAG Posterior for Causal Discovery","display_name":"Coupling Noisy Pairwise Knowledge to the DAG Posterior for Causal Discovery","publication_year":2026,"publication_date":"2026-10-03","ids":{"openalex":"https://openalex.org/W7220728678","doi":"https://doi.org/10.48550/arxiv.2610.04559"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.04559","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04559","pdf_url":"https://arxiv.org/pdf/2610.04559","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.04559","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129713938","display_name":"Guoliang Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Guoliang","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039821435","display_name":"James E. Corter","orcid":"https://orcid.org/0000-0002-5415-8669","observed_orcids":["https://orcid.org/0000-0002-5415-8669"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corter, James E","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"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":1.0,"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":1.0,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/causal-discovery","display_name":"causal discovery","score":0.9869999885559082},{"id":"https://openalex.org/keywords/bayesian-network-structure-learning","display_name":"Bayesian network structure learning","score":0.6830000281333923},{"id":"https://openalex.org/keywords/directed-acyclic-graphs","display_name":"directed acyclic graphs","score":0.7310000061988831},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6570000052452087},{"id":"https://openalex.org/keywords/structural-hamming-distance","display_name":"structural Hamming distance","score":0.6159999966621399}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7512999773025513},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.49050000309944153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4641000032424927},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.43709999322891235},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3986999988555908},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.3140999972820282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C2983394010","wikidata":"https://www.wikidata.org/wiki/Q19885330","display_name":"Continuous variable","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.04559","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04559","pdf_url":"https://arxiv.org/pdf/2610.04559","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":"doi:10.48550/arxiv.2610.04559","doi":"https://doi.org/10.48550/arxiv.2610.04559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.04559","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-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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.04559","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04559","pdf_url":"https://arxiv.org/pdf/2610.04559","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220728678.pdf","grobid_xml":"https://content.openalex.org/works/W7220728678.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4367692219","https://openalex.org/W4391622935","https://openalex.org/W4398796015","https://openalex.org/W7083804128","https://openalex.org/W7164193968"],"related_works":["https://openalex.org/W7169658610","https://openalex.org/W7171531631","https://openalex.org/W4407856861","https://openalex.org/W4417538264","https://openalex.org/W3167743091","https://openalex.org/W7127303128","https://openalex.org/W2949383815","https://openalex.org/W7163893893","https://openalex.org/W7057830759","https://openalex.org/W3158391439"],"abstract_inverted_index":{"External":[0],"causal":[1,31],"reports":[2,32,85],"can":[3],"improve":[4],"structure":[5],"learning":[6],"from":[7,33,129,152],"limited":[8],"observations,":[9],"but":[10],"their":[11],"reliability":[12,80,180],"varies":[13],"across":[14],"sources":[15,34],"and":[16,64,105,110,125,146,183],"variable":[17,144],"pairs.":[18],"We":[19],"introduce":[20],"HB-NoisyKG,":[21],"a":[22,43,47,65,138,171],"Bayesian":[23],"framework":[24],"that":[25],"combines":[26],"observational":[27],"data":[28],"with":[29,142,189],"repeated":[30],"such":[35],"as":[36],"large":[37],"language":[38],"models.":[39],"Each":[40],"report":[41,91,185],"is":[42],"noisy":[44],"observation":[45,101],"of":[46],"direct":[48],"pair":[49,62],"state":[50],"implied":[51],"by":[52,165],"one":[53],"DAG.":[54],"A":[55],"feature-conditioned":[56],"Beta":[57],"prior":[58],"pools":[59],"information":[60],"about":[61],"reliability,":[63],"shared":[66],"error":[67,182],"matrix":[68],"captures":[69],"systematic":[70],"mistakes.":[71],"Alternating":[72],"inference":[73],"uses":[74,93,119],"the":[75,99],"graph":[76,88,95],"posterior":[77],"to":[78,131,156],"refine":[79],"estimates,":[81],"which":[82],"determine":[83],"how":[84],"influence":[86],"subsequent":[87],"updates.":[89],"The":[90],"likelihood":[92],"only":[94],"pair-state":[96],"marginals,":[97],"so":[98],"same":[100],"layer":[102],"supports":[103],"discrete":[104,135],"continuous":[106,159],"likelihoods":[107],"in":[108],"graph-only":[109,161],"joint":[111],"inference.":[112],"Against":[113],"an":[114],"80-restart":[115],"no-KG":[116,155,168],"baseline,":[117],"HB":[118,149],"at":[120],"most":[121],"80":[122],"total":[123],"restarts":[124],"lowers":[126,150],"mean":[127,179],"SHD":[128,151],"22.39":[130],"16.06":[132],"on":[133],"five":[134],"benchmarks.":[136],"On":[137,158],"physical":[139],"light":[140],"tunnel":[141],"random":[143],"IDs":[145],"retained":[147],"descriptions,":[148],"39.00":[153],"for":[154],"27.30.":[157],"Sachs,":[160],"BGe":[162],"raises":[163],"AUROC":[164],"0.121":[166],"over":[167],"Top-K.":[169],"In":[170],"controlled":[172],"synthetic":[173],"study,":[174],"continued":[175],"updating":[176],"also":[177],"reduces":[178],"estimation":[181],"held-out":[184],"log":[186],"loss":[187],"compared":[188],"one-time":[190],"estimation.":[191]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}