{"id":"W4400761863","doi":"10.1016/j.jprocont.2024.103277","title":"Switching probabilistic slow feature extraction for semisupervised industrial inferential modeling","year":2024,"lang":"en","type":"article","venue":"Journal of Process Control","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Probabilistic logic; Artificial intelligence; Feature extraction; Feature (linguistics); Computer science; Inference; Extraction (chemistry); Pattern recognition (psychology); Statistical model; Chromatography; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003929602,0.0001630041,0.0003221721,0.0001917749,0.00006394308,0.0002467431,0.0001196864,0.0001917813,0.00001249123],"category_scores_gemma":[0.0001892628,0.0001328875,0.000207497,0.0001478287,0.000004664003,0.0004710219,0.00000267559,0.0005916537,0.000002880807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124929,"about_ca_system_score_gemma":0.0001206886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002324791,"about_ca_topic_score_gemma":0.000004713963,"domain_scores_codex":[0.9989067,0.00002768934,0.0004925632,0.0001179195,0.0002541055,0.0002010346],"domain_scores_gemma":[0.9994171,0.0001143825,0.00008684408,0.00006770743,0.0002196859,0.00009432493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004740868,0.00002927295,0.00002875981,0.0008477155,0.0004050043,0.00001899325,0.0005427876,0.8982524,0.05691148,0.00007265666,0.000906218,0.04151058],"study_design_scores_gemma":[0.002689583,0.0001028335,0.000002928742,0.0003755217,0.0001621846,0.0001187807,0.0001447649,0.9924575,0.0004571397,0.000440782,0.002907423,0.0001405783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2771761,0.002465835,0.7136486,0.0004424917,0.005225808,0.000618241,0.00001395836,0.0002605082,0.0001483992],"genre_scores_gemma":[0.996985,0.0000128206,0.00007955426,0.00001915671,0.00275775,0.00004886633,0.000001428749,0.00003902494,0.00005641967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7198089,"threshold_uncertainty_score":0.5418997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01860781614661838,"score_gpt":0.2672726625927296,"score_spread":0.2486648464461113,"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."}}