{"id":"https://openalex.org/W7141769904","doi":"https://doi.org/10.48550/arxiv.2603.25473","title":"Causal-INSIGHT: Probing Temporal Models to Extract Causal Structure","display_name":"Causal-INSIGHT: Probing Temporal Models to Extract Causal Structure","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141769904","doi":"https://doi.org/10.48550/arxiv.2603.25473"},"language":"en","primary_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/4750a4b0-782b-4fc7-b6cf-7a9db196d2b3","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/4750a4b0-782b-4fc7-b6cf-7a9db196d2b3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"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":"Redden, B, Wang, H & Li, S 2026, Causal-INSIGHT: probing temporal models to extract causal structure. in 2026 International Joint Conference on Neural Networks (IJCNN): Proceedings. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN ), IEEE, IEEE International Joint Conference on Neural Networks (IJCNN 2026), Maastricht, Netherlands, 21/06/2026.","raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.qub.ac.uk/en/publications/4750a4b0-782b-4fc7-b6cf-7a9db196d2b3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130797985","display_name":"Benjamin Redden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Redden, Benjamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130743566","display_name":"Hui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125153925","display_name":"Shuyan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shuyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12770000100135803,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12770000100135803,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.10930000245571136,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.0608999989926815,"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-structure","display_name":"Causal structure","score":0.6110000014305115},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.5763999819755554},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5220999717712402},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5016999840736389},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.48969998955726624},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48919999599456787},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.43790000677108765},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4011000096797943},{"id":"https://openalex.org/keywords/directed-graph","display_name":"Directed graph","score":0.38519999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6211000084877014},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.6110000014305115},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5503000020980835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.382999986410141},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/4750a4b0-782b-4fc7-b6cf-7a9db196d2b3","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/4750a4b0-782b-4fc7-b6cf-7a9db196d2b3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"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":"Redden, B, Wang, H & Li, S 2026, Causal-INSIGHT: probing temporal models to extract causal structure. in 2026 International Joint Conference on Neural Networks (IJCNN): Proceedings. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN ), IEEE, IEEE International Joint Conference on Neural Networks (IJCNN 2026), Maastricht, Netherlands, 21/06/2026.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2603.25473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25473","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/4750a4b0-782b-4fc7-b6cf-7a9db196d2b3","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/4750a4b0-782b-4fc7-b6cf-7a9db196d2b3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"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":"Redden, B, Wang, H & Li, S 2026, Causal-INSIGHT: probing temporal models to extract causal structure. in 2026 International Joint Conference on Neural Networks (IJCNN): Proceedings. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN ), IEEE, IEEE International Joint Conference on Neural Networks (IJCNN 2026), Maastricht, Netherlands, 21/06/2026.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"directed":[1,76],"temporal":[2,40,77,134],"interactions":[3],"in":[4,133],"multivariate":[5],"time":[6],"series":[7],"is":[8],"essential":[9],"for":[10,30,88],"interpreting":[11],"complex":[12],"dynamical":[13],"systems":[14],"and":[15,90,102,114,129],"the":[16,48,51,82,84],"predictive":[17,100],"models":[18],"trained":[19,39],"on":[20,87],"them.":[21],"We":[22],"present":[23],"Causal-INSIGHT,":[24],"a":[25,57,93],"model-agnostic,":[26],"post-hoc":[27],"interpretation":[28],"framework":[29],"extracting":[31],"model-implied":[32],"(predictor-dependent),":[33],"directed,":[34],"time-lagged":[35],"influence":[36,78],"structure":[37,46],"from":[38],"predictors.":[41,141],"Rather":[42],"than":[43],"inferring":[44],"causal":[45],"at":[47,68],"level":[49],"of":[50],"data-generating":[52],"process,":[53],"Causal-INSIGHT":[54,119],"analyzes":[55],"how":[56],"fixed,":[58],"pre-trained":[59],"predictor":[60,85],"responds":[61],"to":[62,139],"systematic,":[63],"intervention-inspired":[64],"input":[65],"clamping":[66],"applied":[67,138],"inference":[69],"time.":[70],"From":[71],"these":[72],"responses,":[73],"we":[74],"construct":[75],"signals":[79],"that":[80,98,118],"reflect":[81],"dependencies":[83],"relies":[86],"prediction,":[89],"introduce":[91],"Qbic,":[92],"sparsity-aware":[94],"graph":[95,108],"selection":[96],"criterion":[97],"balances":[99],"fidelity":[101],"structural":[103,127],"complexity":[104],"without":[105],"requiring":[106],"ground-truth":[107],"labels.":[109],"Experiments":[110],"across":[111,121],"synthetic,":[112],"simulated,":[113],"realistic":[115],"benchmarks":[116],"show":[117],"generalizes":[120],"diverse":[122],"backbone":[123],"architectures,":[124],"maintains":[125],"competitive":[126],"accuracy,":[128],"yields":[130],"significant":[131],"improvements":[132],"delay":[135],"localization":[136],"when":[137],"existing":[140]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-28T00:00:00"}