{"id":"W7084610053","doi":"10.1016/j.conengprac.2025.106588","title":"StictionGPT: Detecting valve stiction in process control loops using large vision language model","year":2025,"lang":"en","type":"article","venue":"Control Engineering Practice","topic":"Neuropeptides and Animal Physiology","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; Key Technologies Research and Development Program","keywords":"Stiction; Benchmark (surveying); Leverage (statistics); Fault detection and isolation; Unavailability; Process (computing); Generalization; Semantics (computer science)","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":[0.0003319884,0.0001946825,0.0002521967,0.0002074927,0.0001413224,0.00008144428,0.00016114,0.00008215765,0.000005037096],"category_scores_gemma":[0.005602091,0.0002002467,0.00007475074,0.0004326371,0.00001850091,0.0006995604,0.00003987099,0.0004793693,0.00001053358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009044986,"about_ca_system_score_gemma":0.00006296908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003050225,"about_ca_topic_score_gemma":0.000002842977,"domain_scores_codex":[0.9985517,0.0001257704,0.0003106971,0.0004357026,0.0001647928,0.0004113346],"domain_scores_gemma":[0.9983445,0.001193731,0.0001313056,0.000196758,0.00007816539,0.00005555947],"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":[0.0001303329,0.0000606733,0.00001812978,0.00003630519,0.000007328961,0.00001590143,0.00007528482,0.5365461,0.4621491,0.0006760093,0.000002416948,0.00028235],"study_design_scores_gemma":[0.002060029,0.00006980204,0.0003045844,0.0001116368,0.00007120176,0.00001865192,0.0001280319,0.9850021,0.01180023,0.00006025805,0.0002064176,0.0001670262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.422269,0.0001083703,0.5756888,0.0001662003,0.0003957752,0.0004690865,0.00001392826,0.0002511969,0.0006375215],"genre_scores_gemma":[0.9981797,0.000008627197,0.0004307532,0.001193297,0.00008846706,0.00002636189,5.626864e-7,0.00003091585,0.0000412689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5759107,"threshold_uncertainty_score":0.8165824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01101544162400665,"score_gpt":0.3108203138416982,"score_spread":0.2998048722176916,"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."}}