{"id":"W3129019482","doi":"10.48550/arxiv.2102.03954","title":"Large-data determinantal clustering","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Cluster analysis; Determinantal point process; Point process; Mathematics; Correlation clustering; Single-linkage clustering; Clustering high-dimensional data; Data point; Algorithm; Eigenvalues and eigenvectors; Computer science; CURE data clustering algorithm; Random matrix; Statistics","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":[0.003882593,0.000838837,0.00146126,0.0019277,0.001329992,0.002307361,0.002801044,0.001609233,0.001879155],"category_scores_gemma":[0.020808,0.0005596731,0.001126729,0.00279069,0.00141964,0.002541317,0.003642858,0.001944452,0.001503906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051603,"about_ca_system_score_gemma":0.00161992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002893048,"about_ca_topic_score_gemma":0.004781154,"domain_scores_codex":[0.9949781,0.002058812,0.0002470248,0.001186276,0.00126573,0.0002640431],"domain_scores_gemma":[0.9898699,0.003635862,0.0005411362,0.003211429,0.002435421,0.0003061676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004185427,0.000275151,0.008276823,0.000516077,0.0004601155,0.0004184025,0.0009078053,0.5148582,0.01356824,0.1232953,0.02084841,0.316157],"study_design_scores_gemma":[0.00001530486,0.00002358719,0.0009242569,0.00001112625,0.0000135532,0.00007211343,0.0001007154,0.9322797,0.002575374,0.06085907,0.003100806,0.00002438839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01033913,0.0001639735,0.9876747,0.0001752642,0.00003011734,0.00005256948,0.0001971285,0.0006948396,0.0006722813],"genre_scores_gemma":[0.4223484,0.000276377,0.5707118,0.0002257066,0.000113718,0.0002907707,0.003080593,0.0004522999,0.002500373],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003882593,"threshold_uncertainty_score":0.02053332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112099694896418,"score_gpt":0.2060187519646061,"score_spread":0.09391905706818812,"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."}}