{"id":"W2964040819","doi":"10.1609/aaai.v32i1.12221","title":"Clustering - What Both Theoreticians and Practitioners Are Doing Wrong","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Conceptual clustering; Machine learning; Selection (genetic algorithm); Correlation clustering; Artificial intelligence; Task (project management); Implementation; Consensus clustering; Constrained clustering; CURE data clustering algorithm; Data mining; Engineering; Software engineering","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":[0.000380466,0.000111016,0.0001058848,0.00009804005,0.000270466,0.0007614882,0.0004111058,0.00004125009,0.00003791027],"category_scores_gemma":[0.00006240097,0.0000983624,0.00001921178,0.0002602537,0.0002101799,0.002487751,0.0006787847,0.0001353753,0.00005257926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005487163,"about_ca_system_score_gemma":0.00002480005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001674077,"about_ca_topic_score_gemma":0.00005620098,"domain_scores_codex":[0.9987954,0.00007207471,0.0001279433,0.0003843824,0.0002644475,0.0003557862],"domain_scores_gemma":[0.9991611,0.0001672293,0.00005975761,0.0004114503,0.00008599098,0.0001144842],"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":[0.00004116447,0.00006376741,0.000260627,0.00008136281,0.000046113,0.0001192578,0.0063935,0.000927277,0.003734256,0.04246567,0.0003829134,0.9454841],"study_design_scores_gemma":[0.000540398,0.0002542594,0.001440223,0.0002781236,0.000004377534,0.0002157952,0.004063738,0.9751064,0.004947204,0.004873247,0.007803909,0.0004723365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004556783,0.0001041186,0.98546,0.001688429,0.0003191162,0.0001112087,3.412323e-7,0.0002141245,0.007545916],"genre_scores_gemma":[0.5444567,0.0001645459,0.4536871,0.0006445806,0.0002198365,0.00001326289,4.507087e-7,0.00001792269,0.0007956115],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9741791,"threshold_uncertainty_score":0.7343048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0169064493828706,"score_gpt":0.3005511694067407,"score_spread":0.2836447200238701,"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."}}