{"id":"W2079040080","doi":"10.1007/s10618-013-0311-4","title":"A framework for semi-supervised and unsupervised optimal extraction of clusters from hierarchies","year":2013,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Tree (set theory); Cluster (spacecraft); Variety (cybernetics); Data mining; Artificial intelligence; Extraction (chemistry); Machine learning; Mathematics","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":[0.000238731,0.0001713157,0.0002562963,0.0001257743,0.0001670459,0.0003968435,0.0008133908,0.0000904069,0.000005448956],"category_scores_gemma":[0.000309196,0.0001568928,0.00002930959,0.0001910744,0.000170338,0.002814469,0.001429311,0.0001461741,0.000003625193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001629306,"about_ca_system_score_gemma":0.00007075935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001211068,"about_ca_topic_score_gemma":0.00001440823,"domain_scores_codex":[0.9985679,0.00006793963,0.0002550842,0.000650616,0.0001550743,0.0003034252],"domain_scores_gemma":[0.9975732,0.001254727,0.00007298899,0.0008985171,0.00008317818,0.0001173893],"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":[0.0001359583,0.0002143146,0.001263114,0.0004137513,0.0001542915,0.000005941819,0.01339554,0.00009913054,0.008588029,0.001692562,0.001731571,0.9723058],"study_design_scores_gemma":[0.000935589,0.0001868791,0.002974103,0.0003260024,0.00002023509,0.00001071441,0.002441457,0.9881946,0.001106362,0.002765259,0.0007243263,0.0003145053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.369871,0.001067455,0.6282195,0.0001400122,0.000153844,0.0002140402,0.0002439981,0.00003692462,0.00005319574],"genre_scores_gemma":[0.3225427,0.0002250962,0.6765233,0.00003517904,0.0001407261,0.00006279472,0.0002316286,0.00002083375,0.0002177321],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9880955,"threshold_uncertainty_score":0.6397903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06040773208466434,"score_gpt":0.3443362713711306,"score_spread":0.2839285392864663,"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."}}