{"id":"https://openalex.org/W7140201663","doi":"https://doi.org/10.48550/arxiv.2603.20842","title":"A Knowledge-Informed Pretrained Model for Causal Discovery","display_name":"A Knowledge-Informed Pretrained Model for Causal Discovery","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7140201663","doi":"https://doi.org/10.48550/arxiv.2603.20842"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.20842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xu, Wenbo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"He, Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Yunhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yunhai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Xingxuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xingxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kuang, Kun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuang, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Yueguo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yueguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Cui, Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.6735000014305115,"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":0.6735000014305115,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.09799999743700027,"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":0.056299999356269836,"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/robustness","display_name":"Robustness (evolution)","score":0.6761000156402588},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.47859999537467957},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4366999864578247},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.42010000348091125},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.37709999084472656},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3732999861240387},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.3481999933719635},{"id":"https://openalex.org/keywords/business-process-discovery","display_name":"Business process discovery","score":0.3431999981403351}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995999813079834},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6761000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158999800682068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.607200026512146},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C93453677","wikidata":"https://www.wikidata.org/wiki/Q1017580","display_name":"Business process discovery","level":5,"score":0.3431999981403351},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.20842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[{"score":0.47316136956214905,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Causal":[0],"discovery":[1,64],"has":[2],"been":[3],"widely":[4],"studied,":[5],"yet":[6],"many":[7],"existing":[8,131],"methods":[9],"rely":[10],"on":[11,21,120],"strong":[12,30,134],"assumptions":[13],"or":[14,25,32],"fall":[15],"into":[16],"two":[17],"extremes:":[18],"either":[19],"depending":[20],"costly":[22],"interventional":[23],"signals":[24],"partial":[26],"ground":[27],"truth":[28],"as":[29,70],"priors,":[31],"adopting":[33],"purely":[34],"data":[35,86],"driven":[36],"paradigms":[37],"with":[38,133],"limited":[39],"guidance,":[40],"which":[41],"hinders":[42],"practical":[43,137],"deployment.":[44],"Motivated":[45],"by":[46],"real-world":[47,125],"scenarios":[48],"where":[49],"only":[50],"coarse":[51],"domain":[52],"knowledge":[53,69],"is":[54],"available,":[55],"we":[56],"propose":[57],"a":[58,71,78,88,93,98],"knowledge-informed":[59,89],"pretrained":[60],"model":[61,76,106],"for":[62],"causal":[63],"that":[65,102],"integrates":[66],"weak":[67],"prior":[68,109],"principled":[72],"middle":[73],"ground.":[74],"Our":[75],"adopts":[77],"dual":[79],"source":[80],"encoder-decoder":[81],"architecture":[82],"to":[83,107],"process":[84],"observational":[85],"in":[87],"way.":[90],"We":[91],"design":[92],"diverse":[94],"pretraining":[95],"dataset":[96],"and":[97,115,124,136],"curriculum":[99],"learning":[100],"strategy":[101],"smoothly":[103],"adapts":[104],"the":[105],"varying":[108],"strengths":[110],"across":[111],"mechanisms,":[112],"graph":[113],"densities,":[114],"variable":[116],"scales.":[117],"Extensive":[118],"experiments":[119],"in-distribution,":[121],"out-of":[122],"distribution,":[123],"datasets":[126],"demonstrate":[127],"consistent":[128],"improvements":[129],"over":[130],"baselines,":[132],"robustness":[135],"applicability.":[138]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}