{"id":"W7133093713","doi":"","title":"Optimal and Greedy Algorithms for Clustering with Applications to Data Science","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Constrained clustering; Correlation clustering; Scalability; Class (philosophy); Heuristic; Bounding overwatch; CURE data clustering algorithm; Clustering high-dimensional data","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","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001777265,0.0006782521,0.0006208192,0.001001276,0.001832004,0.001581073,0.006737921,0.0001987189,0.000008321525],"category_scores_gemma":[0.0003756305,0.0006904232,0.00004892282,0.004438348,0.0006263697,0.001745666,0.005440958,0.0005954309,0.0001099306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002942082,"about_ca_system_score_gemma":0.001401715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003710412,"about_ca_topic_score_gemma":0.0004204306,"domain_scores_codex":[0.9923993,0.00004660165,0.0005335947,0.003699931,0.00167183,0.001648684],"domain_scores_gemma":[0.9932569,0.0005087644,0.000311244,0.003856864,0.001166645,0.0008995304],"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":[0.0004547205,0.0001820086,0.00001967817,0.001718443,0.0001643464,0.00005706851,0.03144994,0.06120737,0.006485455,0.0008995365,0.0003796507,0.8969818],"study_design_scores_gemma":[0.0006904766,0.0006890484,0.000514354,0.0004304967,0.00004767532,0.00006040159,0.00683982,0.9836214,0.0009889967,0.00005604211,0.005153757,0.0009075355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003458745,0.0001991762,0.989775,0.001060955,0.0005533334,0.004220217,0.0001358538,0.0003215517,0.0002751519],"genre_scores_gemma":[0.004714737,0.0001983296,0.9768134,0.00006793395,0.0004351909,0.002097291,0.0003801674,0.0001874031,0.01510557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.922414,"threshold_uncertainty_score":0.9995547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.123146208373665,"score_gpt":0.4590791525163828,"score_spread":0.3359329441427178,"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."}}