{"id":"W4313495625","doi":"10.31449/inf.v46i4.3476","title":"OMCOKE: A Machine Learning Outlier-based Overlapping Clustering Technique for Multi-Label Data Analysis","year":2022,"lang":"en","type":"article","venue":"Informatica","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fanshawe College","funders":"","keywords":"Cluster analysis; Outlier; Computer science; Anomaly detection; Data mining; Artificial intelligence; Unsupervised learning; Cluster (spacecraft); CURE data clustering algorithm; Machine learning; Pattern recognition (psychology); Correlation clustering","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":[0.0008078322,0.0001351325,0.0002152319,0.0005366942,0.0005578237,0.0002401763,0.002374854,0.00004366831,0.00004184322],"category_scores_gemma":[0.0002370178,0.0001331248,0.00007420864,0.001168358,0.00003321456,0.000957998,0.002008992,0.0002759109,0.00001148343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009226066,"about_ca_system_score_gemma":0.00006702463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001998716,"about_ca_topic_score_gemma":0.000009643749,"domain_scores_codex":[0.9986808,0.00004002984,0.0004334117,0.0002755359,0.000298876,0.0002713785],"domain_scores_gemma":[0.9982278,0.0001384908,0.0002712599,0.001277529,0.00004296303,0.00004199574],"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":[0.0001412787,0.001172251,0.009117218,0.0008519482,0.001615518,0.0000184458,0.007230658,0.1246318,0.008533042,0.08329624,0.006664365,0.7567273],"study_design_scores_gemma":[0.0004715898,0.0000752695,0.0001247416,0.0000057323,0.00004108562,0.000002648575,0.0002386244,0.980212,0.0004171626,0.0001802747,0.01805778,0.0001731143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002273274,0.00003788718,0.9971337,0.0008799319,0.00006496393,0.0004874584,0.00005508096,0.0007895619,0.0003241019],"genre_scores_gemma":[0.2596744,0.000003565087,0.7389923,0.0003336512,0.000004847439,0.000519328,0.0002309414,0.000008555696,0.0002324459],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8555802,"threshold_uncertainty_score":0.542867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09572787538383581,"score_gpt":0.3254020660487998,"score_spread":0.229674190664964,"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."}}