{"id":"W2113334100","doi":"10.1016/j.jbi.2008.11.004","title":"Efficient layered density-based clustering of categorical data","year":2008,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Data mining; Scalability; CURE data clustering algorithm; Single-linkage clustering; Clustering high-dimensional data; Correlation clustering; Artificial intelligence; Pattern recognition (psychology); Machine learning; Database","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":[0.001085795,0.0001174847,0.0003530254,0.0003714281,0.00009293487,0.00003470117,0.002286979,0.00009028076,0.000006971892],"category_scores_gemma":[0.000498022,0.00008895771,0.00007825525,0.0006715061,0.000272501,0.0003759114,0.00112002,0.000425628,0.00001143931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009531719,"about_ca_system_score_gemma":0.0005081319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005363413,"about_ca_topic_score_gemma":4.168766e-7,"domain_scores_codex":[0.9968574,0.0000522692,0.001190809,0.00009278053,0.001494576,0.000312182],"domain_scores_gemma":[0.997626,0.0002785158,0.000625648,0.000755262,0.0003777258,0.0003368287],"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":[0.0004545863,0.003108219,0.0005785509,0.001931501,0.0004898063,0.003203416,0.01501278,0.6147596,0.004797563,0.001083358,0.01679852,0.3377821],"study_design_scores_gemma":[0.0007737466,0.0002803119,0.0001875065,0.00005505968,0.0000050504,0.001003053,0.00007500374,0.9949704,0.0005757519,0.00005132044,0.001931487,0.00009134017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02572642,0.00004048108,0.9732424,0.0004691275,0.0003665901,0.00006303281,0.000005713385,0.00002055521,0.00006570068],"genre_scores_gemma":[0.490979,0.00002221874,0.508755,0.0001327831,0.0000907018,4.043929e-7,0.000004184702,0.00000587634,0.000009848502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4652526,"threshold_uncertainty_score":0.4249813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06798969841812494,"score_gpt":0.3235346120781342,"score_spread":0.2555449136600092,"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."}}