{"id":"W2093156537","doi":"10.1007/s10044-007-0088-4","title":"Hierarchical clustering of subpopulations with a dissimilarity based on the likelihood ratio statistic: application to clustering massive data sets","year":2007,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Cluster analysis; Mathematics; Statistic; Hierarchical clustering; Multinomial distribution; Poisson distribution; Multivariate normal distribution; Statistics; Data mining; Computer science; Multivariate statistics","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":[0.0006673663,0.0001554515,0.0002239947,0.0003152659,0.0003491359,0.0001376444,0.001032978,0.00003784699,0.000008308174],"category_scores_gemma":[0.00004234431,0.0001144804,0.00004171809,0.001742317,0.00008122114,0.0001556197,0.0005849554,0.0001888452,0.0000049594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000480169,"about_ca_system_score_gemma":0.0000390021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002676315,"about_ca_topic_score_gemma":0.00263137,"domain_scores_codex":[0.9981647,0.00006993183,0.000360239,0.0006531398,0.0004560215,0.0002959718],"domain_scores_gemma":[0.997193,0.0005433051,0.0001592143,0.001776598,0.0001427892,0.0001851279],"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":[0.00004004299,0.0002845246,0.01822561,0.00006918236,0.000274301,0.000004575236,0.0004672343,0.1810209,0.001194415,0.003080185,0.0000299329,0.7953091],"study_design_scores_gemma":[0.0001318638,0.00004298945,0.06852243,0.00001458852,0.00007491389,0.000001242111,0.00005397433,0.9303702,0.0002021109,0.0002937263,0.0001625529,0.0001294797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001596481,0.000006336986,0.9946455,0.002746436,0.000006355433,0.0006715439,0.0001959178,0.00004629654,0.00008512827],"genre_scores_gemma":[0.8774816,0.000002919872,0.1217878,0.000276229,0.00002873138,0.0002365725,0.0001654137,0.00001134169,0.000009360572],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8758851,"threshold_uncertainty_score":0.4668376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03091776160389113,"score_gpt":0.3354578783523037,"score_spread":0.3045401167484125,"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."}}