{"id":"W2804364458","doi":"10.1609/aaai.v32i1.12221","title":"Clustering - What Both Theoreticians and Practitioners Are Doing Wrong","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Selection (genetic algorithm); Task (project management); Conceptual clustering; Correlation clustering; Machine learning; Implementation; Consensus clustering; Constrained clustering; CURE data clustering algorithm; Artificial intelligence; Data mining; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001230205,0.0004757962,0.0005104835,0.0002759078,0.0004100416,0.002044245,0.003290164,0.0002851355,0.00003359215],"category_scores_gemma":[0.0006699455,0.0003910909,0.0001451224,0.0005106658,0.0009767865,0.001726287,0.005512256,0.001212202,0.00003663872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001649005,"about_ca_system_score_gemma":0.0001869128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004026326,"about_ca_topic_score_gemma":0.00001739007,"domain_scores_codex":[0.9964628,0.00006766571,0.0007096186,0.0011981,0.0009282824,0.0006335587],"domain_scores_gemma":[0.9968181,0.0002657738,0.001010163,0.0007354099,0.0009988345,0.0001717787],"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":[0.0002691098,0.0002717251,0.0000983936,0.001173345,0.0001392361,0.00001040737,0.011774,0.002900906,0.01244987,0.4435882,0.0001270454,0.5271978],"study_design_scores_gemma":[0.00004346682,0.0002309865,0.0001082218,0.005028245,0.00002718241,0.00002844481,0.004322892,0.6176339,0.111357,0.2604046,0.0001227089,0.0006923238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04613931,0.0003011083,0.9292779,0.01059861,0.002955324,0.001621614,0.00001590172,0.0003730857,0.008717125],"genre_scores_gemma":[0.9454822,0.0008916643,0.05277827,0.0002739273,0.0002632361,0.00008789232,0.000001022169,0.00004511326,0.0001766576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8993429,"threshold_uncertainty_score":0.9998541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0757605411064104,"score_gpt":0.3368907167482257,"score_spread":0.2611301756418153,"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."}}