{"id":"W2137690751","doi":"10.1016/j.compchemeng.2004.01.009","title":"On-line outlier detection and data cleaning","year":2004,"lang":"en","type":"article","venue":"Computers & Chemical Engineering","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":431,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Anomaly detection; Outlier; Line (geometry); Computer science; Data mining; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000306102,0.0001417333,0.0001889542,0.00009184769,0.00005569925,0.000120392,0.000582889,0.00005463646,0.0000038138],"category_scores_gemma":[0.002746344,0.0001262579,0.00002051536,0.0002785444,0.0000395788,0.0002940867,0.0004320844,0.0002603657,0.00002813172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006580996,"about_ca_system_score_gemma":0.000009438836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002192359,"about_ca_topic_score_gemma":1.973174e-7,"domain_scores_codex":[0.9984361,0.000006401163,0.000301768,0.0005626142,0.0004600113,0.0002331129],"domain_scores_gemma":[0.9982817,0.0009547562,0.0000493864,0.0005058405,0.00004998426,0.0001583061],"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":[0.00002784295,0.00003415571,0.00002154826,0.00002191366,0.00001559763,0.00002895224,0.0001407754,0.6488472,0.05304279,0.003393148,0.00007076264,0.2943554],"study_design_scores_gemma":[0.000569121,0.00005047923,0.0001200049,0.00008436772,0.000006993277,0.00002183919,0.00001976586,0.9445537,0.03344424,0.02012239,0.0007408084,0.000266272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09027544,0.00005893782,0.9089016,0.00008533298,0.0004623395,0.00004649851,0.000005264975,0.0001202049,0.00004433363],"genre_scores_gemma":[0.906108,0.000001446403,0.09359632,0.0000535741,0.0002128701,0.000001858357,0.000003255681,0.00001667231,0.0000059914],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8158326,"threshold_uncertainty_score":0.5148646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0930221500322236,"score_gpt":0.3712197622785883,"score_spread":0.2781976122463647,"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."}}