{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004055087,0.00200916,0.001818172,0.002029874,0.001580907,0.002583912,0.002546459,0.002192725,0.004324626],"category_scores_gemma":[0.01467507,0.001050874,0.001799595,0.004532229,0.002789458,0.003636192,0.00331574,0.004595813,0.002167296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003346434,"about_ca_system_score_gemma":0.004355688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004100488,"about_ca_topic_score_gemma":0.005364583,"domain_scores_codex":[0.9970655,0.001160931,0.0001602836,0.0006463343,0.0007834157,0.0001834828],"domain_scores_gemma":[0.9935191,0.004228936,0.0003769514,0.0008449286,0.0008471736,0.0001828892],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008751658,0.00009362031,0.0005542875,0.0004678931,0.00009992506,0.00006078897,0.0002057363,0.4064524,0.001232881,0.4076006,0.01468669,0.1684576],"study_design_scores_gemma":[0.00003030896,0.00002982586,0.0001097611,0.00005805028,0.00001546823,0.0000439925,0.0000492123,0.6173366,0.0007814887,0.3720173,0.0095066,0.00002125081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001110657,0.0007225196,0.994783,0.0005236852,0.00007461323,0.0000510142,0.00006688529,0.0002602875,0.002407306],"genre_scores_gemma":[0.03824073,0.00169537,0.9557021,0.0003336348,0.0002195951,0.0003366118,0.0003443556,0.0003152381,0.002812313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004324626,"threshold_uncertainty_score":0.02428013,"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."}}