{"id":"W3103821869","doi":"10.36001/phmconf.2020.v12i1.1136","title":"Automatic detection of rare observations during production tests using statistical models","year":2020,"lang":"en","type":"article","venue":"Annual Conference of the PHM Society","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Safran Electronics (Canada)","funders":"CHIST-ERA; Safran Aircraft Engines; Safran; Association Nationale de la Recherche et de la Technologie","keywords":"Interpretability; Computer science; Cluster analysis; Context (archaeology); Machine learning; Anomaly detection; Representation (politics); Artificial intelligence; Data mining; Feature (linguistics); Variable (mathematics); Pattern recognition (psychology); Mathematics","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":[0.002019518,0.001071306,0.001025415,0.003870726,0.0003714354,0.001498802,0.001665472,0.001011377,0.0006389091],"category_scores_gemma":[0.007561888,0.0005201183,0.001210263,0.002194242,0.0005234758,0.001511281,0.001116323,0.00124222,0.0006605255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006125966,"about_ca_system_score_gemma":0.0009542047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004020649,"about_ca_topic_score_gemma":0.005527665,"domain_scores_codex":[0.9980755,0.0004039475,0.0001349065,0.0005392175,0.0006743816,0.0001720311],"domain_scores_gemma":[0.9928505,0.003990262,0.001402318,0.0006854163,0.0008650377,0.0002063884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006748955,0.0005556831,0.1142543,0.0003053482,0.0004184491,0.001374517,0.0006327854,0.3614244,0.03742069,0.008332604,0.006841648,0.4677646],"study_design_scores_gemma":[0.000004744612,0.0000232174,0.00406277,0.000009235307,0.0000128436,0.0001086036,0.00003608645,0.9891948,0.002845812,0.003195666,0.0004936805,0.00001260398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1127296,0.0002801788,0.8788316,0.000207611,0.00005021059,0.00007001191,0.0006512617,0.006268093,0.0009115018],"genre_scores_gemma":[0.7941181,0.0002010658,0.2024774,0.00006287431,0.00006044731,0.0001046845,0.001945392,0.0002402279,0.0007897169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004020649,"threshold_uncertainty_score":0.01068038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0841597462602211,"score_gpt":0.2752207354733761,"score_spread":0.191060989213155,"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."}}