{"id":"W2012187238","doi":"10.1109/isspa.2012.6310493","title":"Improving X-means clustering with MNDL","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Bayesian information criterion; Determining the number of clusters in a data set; Computer science; Correlation clustering; Single-linkage clustering; Set (abstract data type); Cluster (spacecraft); Data mining; CURE data clustering algorithm; Mathematics; Algorithm; 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":[0.0002572245,0.0001164112,0.0000986328,0.00008225173,0.0001208411,0.0001248696,0.0006494838,0.00003029735,0.00002366049],"category_scores_gemma":[0.00002465804,0.00008719511,0.00002186738,0.0003090771,0.00003461157,0.001372267,0.0006379445,0.0001525131,0.0001086954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007195216,"about_ca_system_score_gemma":0.00003222781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005885102,"about_ca_topic_score_gemma":0.00001733922,"domain_scores_codex":[0.9986316,0.00002609201,0.0001110967,0.0002487373,0.0003337395,0.0006487304],"domain_scores_gemma":[0.9991004,0.0000585265,0.00003364211,0.000546351,0.00005380263,0.0002072858],"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":[0.00002095232,0.0001378893,0.003563431,0.00008448464,0.00003474156,0.0000389052,0.002002463,0.004847222,0.008039496,0.01238042,0.0001634504,0.9686865],"study_design_scores_gemma":[0.0004544343,0.0001443545,0.002051676,0.00002154499,0.000002528481,0.0001725826,0.0001214654,0.986294,0.006574118,0.00009659856,0.003703106,0.0003635539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00273387,0.00005035087,0.9885185,0.000206072,0.0001670246,0.0001049009,2.528286e-7,0.0003389653,0.007880074],"genre_scores_gemma":[0.3911584,0.000001836608,0.6068986,0.0001134639,0.0001151935,0.00001467762,2.731628e-7,0.00001372386,0.001683808],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9814468,"threshold_uncertainty_score":0.3555714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01956843432714596,"score_gpt":0.274819099399345,"score_spread":0.255250665072199,"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."}}