{"id":"W2995714961","doi":"10.1109/cwit.2019.8929909","title":"Correct Number of Clusters (CNC) Description Length in Arbitrary Shape Clustering","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Computer science; Cluster (spacecraft); k-medians clustering; Determining the number of clusters in a data set; Compact space; Separable space; Context (archaeology); Data mining; Point (geometry); Algorithm; Correlation clustering; Mathematics; Artificial intelligence; CURE data clustering algorithm","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":[0.0003915284,0.0001610201,0.0002586468,0.0002053522,0.00002986706,0.00007370854,0.0008664904,0.00008068046,0.0001678626],"category_scores_gemma":[0.00003609988,0.000156257,0.00006446984,0.0006093612,0.0000425513,0.001115923,0.0007109219,0.0002861143,0.0002749635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001439151,"about_ca_system_score_gemma":0.00006865088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001640821,"about_ca_topic_score_gemma":0.00005291155,"domain_scores_codex":[0.9981829,0.00009070725,0.0003649409,0.0004768005,0.0004353434,0.0004493417],"domain_scores_gemma":[0.9989924,0.0001403663,0.00008338068,0.0006236059,0.00007197873,0.00008820731],"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":[0.0003218892,0.0006665515,0.09115517,0.0008376791,0.00009757194,0.0001716283,0.005775541,0.06218996,0.03418599,0.008698235,0.000562122,0.7953377],"study_design_scores_gemma":[0.0006598374,0.00007961368,0.006504429,0.000088541,0.000001006539,0.00004871636,0.0001376253,0.9896563,0.001872045,0.0005442738,0.0002037748,0.000203797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3724263,0.00002050756,0.603244,0.0001484801,0.0005896969,0.0003277706,0.000001005414,0.0001415959,0.02310069],"genre_scores_gemma":[0.8681637,0.00002252208,0.1297427,0.0001457476,0.00002501947,0.00001355375,0.000001643453,0.0000185404,0.001866546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9274664,"threshold_uncertainty_score":0.6371976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02317612935228306,"score_gpt":0.2908982372374981,"score_spread":0.267722107885215,"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."}}