{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004712904,0.00117388,0.002136,0.003472786,0.001937464,0.003710632,0.004754857,0.001975002,0.002734884],"category_scores_gemma":[0.01164817,0.001068743,0.002507082,0.004050041,0.002121405,0.003801972,0.004615476,0.002957153,0.001830198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001660069,"about_ca_system_score_gemma":0.003871193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008027991,"about_ca_topic_score_gemma":0.01518997,"domain_scores_codex":[0.9961482,0.001162313,0.0003094972,0.0008732014,0.001257979,0.0002488778],"domain_scores_gemma":[0.9951792,0.001775514,0.0003824513,0.001027828,0.001393923,0.0002410205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002108904,0.0002091988,0.001290277,0.0005154728,0.0002858337,0.0002536786,0.0008870711,0.1577751,0.01065595,0.2780117,0.01594564,0.5339591],"study_design_scores_gemma":[0.00003342421,0.00004685997,0.0003688262,0.00006355796,0.00005094475,0.0001592612,0.0001190532,0.7681822,0.002756648,0.2180263,0.01014296,0.00005003229],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003578806,0.00006508255,0.999009,0.00004375724,0.000009231741,0.00002323801,0.0000526012,0.0002874676,0.0001516203],"genre_scores_gemma":[0.01760601,0.0001191692,0.9808699,0.00005842078,0.00004026802,0.0001329232,0.0003835343,0.0001414221,0.0006483616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008027991,"threshold_uncertainty_score":0.02492452,"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."}}