{"id":"W4411171734","doi":"10.1371/journal.pone.0321968","title":"Explainable one-class feature extraction by adaptive resonance for anomaly detection in quality assurance","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Quality assurance; Feature (linguistics); Class (philosophy); Computer science; Anomaly detection; Feature extraction; Anomaly (physics); Artificial intelligence; Pattern recognition (psychology); Physics; Medicine; Pathology; External quality assessment; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001935671,0.0008229885,0.0006937535,0.001574408,0.0004913021,0.0008641108,0.001332856,0.001115075,0.0013459],"category_scores_gemma":[0.006486591,0.0002981918,0.00106098,0.0010597,0.0008550989,0.001266697,0.001020833,0.001624468,0.0004227204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009214683,"about_ca_system_score_gemma":0.0009844534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003730619,"about_ca_topic_score_gemma":0.00322862,"domain_scores_codex":[0.9987031,0.0003084659,0.00006347464,0.0003927967,0.0003882357,0.0001438496],"domain_scores_gemma":[0.9965622,0.001906166,0.000455929,0.0003704891,0.0006349009,0.00007031751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003253607,0.0002338186,0.006815513,0.0001762095,0.0001244617,0.0002586219,0.0003657471,0.2877044,0.03088837,0.009820368,0.00247991,0.6608072],"study_design_scores_gemma":[0.000004833864,0.00003074791,0.0009374512,0.000007366701,0.00001433876,0.00005122358,0.00001677377,0.9896834,0.003788429,0.004747954,0.0007044103,0.00001307239],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02020936,0.0001256553,0.9781706,0.0001398422,0.0000272324,0.000038517,0.00004738205,0.0007471251,0.000494345],"genre_scores_gemma":[0.5949354,0.0001683851,0.4026623,0.0001573718,0.00008275029,0.0001368349,0.0003407939,0.0001947532,0.001321359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003730619,"threshold_uncertainty_score":0.01023698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03825933420234588,"score_gpt":0.2835435802032786,"score_spread":0.2452842460009327,"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."}}