{"id":"W7116362083","doi":"10.1016/j.knosys.2025.115154","title":"DVAE: A Dynamic Variational Autoencoder for Structured Causal Discovery with Application in Biomedical Time Series","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Autoencoder; Spurious relationship; Causal inference; Noise (video); Inference; Deep learning; Sequence (biology); Time series","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004032322,0.0001943823,0.0002790127,0.0002776766,0.0001193662,0.0002523056,0.0005088153,0.0001437063,0.000001733784],"category_scores_gemma":[0.00004044796,0.0001593312,0.00004635811,0.0007548549,0.00007987483,0.000368403,0.00005468806,0.0001358557,0.00001874389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002042218,"about_ca_system_score_gemma":0.001019443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006236857,"about_ca_topic_score_gemma":0.0001794324,"domain_scores_codex":[0.9984732,0.0001140024,0.0003799544,0.0005245156,0.0002195581,0.0002887138],"domain_scores_gemma":[0.9989833,0.0002039858,0.0001048118,0.0004427489,0.0001959703,0.00006923277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004667251,0.000964956,0.00309997,0.001732958,0.000211487,0.0000152186,0.001484664,0.08722185,0.01074301,0.8734866,0.003648406,0.0169242],"study_design_scores_gemma":[0.0008277548,0.0001011425,0.001116995,0.0002262689,0.00001169049,0.000006326414,0.00001605235,0.9922118,0.000100792,0.003957759,0.00123198,0.0001914118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001482941,0.0002307121,0.9959929,0.0006714565,0.0004732535,0.0006273637,0.00004020051,0.0001617508,0.000319445],"genre_scores_gemma":[0.9620167,8.313949e-7,0.03561345,0.00005843017,0.00006820581,0.0005511324,0.0001092004,0.00001344492,0.001568615],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9605337,"threshold_uncertainty_score":0.6497339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006673129385924043,"score_gpt":0.2539337208812106,"score_spread":0.2472605914952865,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}