{"id":"W2952893570","doi":"10.48550/arxiv.1704.00352","title":"Simple Measures of Individual Cluster-Membership Certainty for Hard Partitional Clustering","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Silhouette; Cluster analysis; Single-linkage clustering; Fuzzy clustering; Hierarchical clustering; Pattern recognition (psychology); Correlation clustering; Complete-linkage clustering; k-medians clustering; Mathematics; Medoid; Determining the number of clusters in a data set; Data mining; Computer science; Partition (number theory); Artificial intelligence; CURE data clustering algorithm; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001108272,0.0003185118,0.0004929355,0.0001995256,0.0002802165,0.0002052284,0.002755013,0.0003573875,0.00001712349],"category_scores_gemma":[0.0001395808,0.0003549432,0.0003985176,0.0001161596,0.0001554347,0.0003736821,0.002214539,0.0003927125,0.000004590399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009361456,"about_ca_system_score_gemma":0.0002855684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007917819,"about_ca_topic_score_gemma":0.000102288,"domain_scores_codex":[0.9979156,0.0002293804,0.00028282,0.0009816795,0.0001802305,0.0004102421],"domain_scores_gemma":[0.9973041,0.0002607373,0.0005257544,0.001434939,0.0002933198,0.0001811124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002998254,0.0002532821,0.002112831,0.0009049007,0.0007060452,0.00008992544,0.0014053,0.1548569,0.0001444277,0.8121538,0.004448868,0.02262395],"study_design_scores_gemma":[0.0009092976,0.00007685705,0.001316761,0.0001406432,0.0001354695,0.000004570813,0.00002113077,0.4464084,0.0004100415,0.5488725,0.001215697,0.0004885966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01459116,0.00004939668,0.9823401,0.0001588363,0.0005826949,0.0004766993,0.0001538971,0.00009164065,0.001555573],"genre_scores_gemma":[0.9018664,0.00002683018,0.09724183,0.0001116099,0.0001441877,0.000004790071,0.00004398374,0.00001920449,0.000541183],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8872752,"threshold_uncertainty_score":0.9998903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2349758300310732,"score_gpt":0.2552991558231561,"score_spread":0.02032332579208287,"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."}}