{"id":"W4377289092","doi":"10.1038/s41746-023-00816-9","title":"Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Computer science; Artificial intelligence; Inference; Masking (illustration); Machine learning; Cluster analysis; Association (psychology); Closing (real estate); Knowledge extraction; Class (philosophy); Data mining; Data science; Psychology","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":[0.0003523298,0.00007342065,0.0001551072,0.0001281717,0.00001559459,0.00006028663,0.0001927243,0.00001929678,0.000002432433],"category_scores_gemma":[0.00009413492,0.00005829266,0.000008832162,0.0002007794,0.0001011872,0.0008031534,0.0002200092,0.00004169223,0.000003526638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002913515,"about_ca_system_score_gemma":0.0000114851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008044671,"about_ca_topic_score_gemma":0.000002471014,"domain_scores_codex":[0.9992027,0.00002964332,0.0002390728,0.0002152167,0.0002015671,0.0001117562],"domain_scores_gemma":[0.9993875,0.0002146374,0.00007443575,0.0002599549,0.00002338398,0.00004011175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00004635943,0.0001449661,0.04396696,0.0007502299,0.00007269905,0.00004181296,0.003829717,0.00000310567,0.01591366,0.6387327,0.003786905,0.2927109],"study_design_scores_gemma":[0.007392813,0.00216328,0.6842173,0.008713538,0.0001008242,0.0001790347,0.01177199,0.06877761,0.03046263,0.1756845,0.008929668,0.001606817],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2434953,0.000350979,0.7468653,0.003389981,0.0001839458,0.0005570875,0.0001130872,0.000338559,0.004705773],"genre_scores_gemma":[0.9992707,0.00005242184,0.000257523,0.0001157749,0.00002165827,0.00002774142,0.00005662383,0.000004856653,0.0001926943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7557754,"threshold_uncertainty_score":0.2377106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03190714840485959,"score_gpt":0.2765683581320183,"score_spread":0.2446612097271587,"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."}}