{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003076751,0.0002733362,0.000276374,0.0001761213,0.0001584211,0.0005796512,0.006303817,0.000152289,0.00004706],"category_scores_gemma":[0.00002174284,0.0003324747,0.000116903,0.0004292449,0.00004078859,0.001644558,0.03499074,0.0004057498,0.00009209402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007753105,"about_ca_system_score_gemma":0.0001047011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006892456,"about_ca_topic_score_gemma":0.0001969466,"domain_scores_codex":[0.9976064,0.00008507873,0.0001658277,0.001620651,0.0001043606,0.0004177056],"domain_scores_gemma":[0.9958432,0.00003517841,0.0001569155,0.003783827,0.00005891188,0.0001219368],"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":[0.0001539636,0.00364593,0.02644783,0.004020804,0.003264649,0.1061117,0.005192633,0.1823457,0.00023855,0.4330107,0.04447875,0.1910888],"study_design_scores_gemma":[0.0003139308,0.00001334891,0.000538726,0.00009600179,0.0000516015,0.000007882682,0.0001563434,0.9923954,0.00002213524,0.001273201,0.004708419,0.0004229796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03616193,0.00007867433,0.9596286,0.00006279101,0.001268501,0.0001597363,0.00009583144,0.000251817,0.00229214],"genre_scores_gemma":[0.986464,0.0002376625,0.009995152,0.0001225215,0.0001268675,3.994069e-7,0.0004460961,0.00001722532,0.002590054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9503021,"threshold_uncertainty_score":0.9999127,"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."}}