{"id":"W2100405508","doi":"10.1109/nafips.2008.4531218","title":"Discovering structure in labeled data","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Hierarchical clustering; Class (philosophy); Similarity (geometry); Data mining; Measure (data warehouse); Cluster (spacecraft); Artificial intelligence; Similarity measure; Data structure; Pattern recognition (psychology); Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.00008038976,0.00006941113,0.00008635031,0.00007595147,0.00005864012,0.00004214111,0.001934628,0.00002500986,0.00002254492],"category_scores_gemma":[0.00005592777,0.0000586341,0.000007142628,0.0004065184,0.00003118003,0.00104424,0.002018839,0.0001542413,0.00001820483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003760554,"about_ca_system_score_gemma":0.00005347908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001024195,"about_ca_topic_score_gemma":0.0001372266,"domain_scores_codex":[0.9989941,0.00002230602,0.0001072543,0.0003729423,0.0002444722,0.0002589686],"domain_scores_gemma":[0.9986738,0.00004436893,0.00001472121,0.001199443,0.00001667767,0.00005097024],"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":[0.00007025237,0.0005055043,0.05464252,0.0001865187,0.00009500107,0.005159591,0.009097531,0.07507145,0.07739888,0.05470975,0.006699983,0.716363],"study_design_scores_gemma":[0.0005323957,0.00002736631,0.01397519,0.00001244905,3.130407e-7,0.0001444557,0.00002375134,0.9770824,0.00370138,0.001423741,0.002862331,0.0002142525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1999109,0.00005894785,0.798314,0.0003778471,0.000112419,0.00009033388,0.00000744662,0.0001245503,0.001003494],"genre_scores_gemma":[0.7467431,0.00002280112,0.2523881,0.00006099732,0.00002970491,0.000001675462,0.000005666896,0.000005865986,0.0007420379],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9020109,"threshold_uncertainty_score":0.3595053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08347915006166517,"score_gpt":0.329163074094694,"score_spread":0.2456839240330288,"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."}}