{"id":"W2137960471","doi":"10.1109/icdm.2006.159","title":"The PDD Framework for Detecting Categories of Peculiar Data","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Data set; Set (abstract data type); Outlier; Oracle; Data mining; Extensibility; Data structure; Information retrieval; Artificial intelligence","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":[0.0002647722,0.00005984644,0.00006568737,0.00002364679,0.0003571898,0.0001403808,0.00109382,0.00004106189,6.71667e-7],"category_scores_gemma":[0.0001103928,0.0000443032,0.00002754526,0.0002797768,0.00005033179,0.0002666012,0.0002620511,0.00007447291,0.000001783096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001031425,"about_ca_system_score_gemma":0.00001611132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003926988,"about_ca_topic_score_gemma":0.000003841223,"domain_scores_codex":[0.999376,0.000001374726,0.0001661929,0.0002193488,0.00009751978,0.0001395803],"domain_scores_gemma":[0.9992817,0.0001038664,0.0001382857,0.0003051556,0.0001546732,0.00001634295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001699886,0.000008718289,0.0001805628,0.00001295048,0.000002683659,1.828463e-8,0.00006734078,4.774066e-7,0.001436504,0.9762825,0.00194284,0.02006369],"study_design_scores_gemma":[0.00006206879,0.00005787091,0.0004837166,0.00001573681,0.000008460082,0.000006261896,0.0001682008,0.02060637,0.1158192,0.7355455,0.1270981,0.0001286361],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003623495,0.00009592951,0.9931043,0.001168417,0.00004891323,0.0002148213,0.000003641209,0.0001954006,0.001545024],"genre_scores_gemma":[0.7388476,0.00001095724,0.2607841,0.00002817532,0.0001049215,0.00008883377,0.000001078265,0.000005438394,0.0001289526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7352241,"threshold_uncertainty_score":0.2747251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02736885025873735,"score_gpt":0.2854560139085606,"score_spread":0.2580871636498232,"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."}}