{"id":"W2979333226","doi":"10.1109/ccece.2019.8861966","title":"Semiparametric Subsampling and Data Condensation for Large-Scale Data Analytics","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Data mining; Benchmark (surveying); Artificial intelligence; Scalability; Pattern recognition (psychology); Random forest; Voronoi diagram; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.001044022,0.00006845079,0.00009975056,0.000102613,0.00007556158,0.0002431137,0.001639997,0.00004032451,0.00001615815],"category_scores_gemma":[0.0003318024,0.00006033646,0.000007569617,0.0003280069,0.000007737363,0.001006841,0.001162309,0.00007692603,0.00004302322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008166866,"about_ca_system_score_gemma":0.00003276541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003002303,"about_ca_topic_score_gemma":0.00003960145,"domain_scores_codex":[0.9988974,0.00002731777,0.0001524991,0.00063185,0.0001409392,0.0001499871],"domain_scores_gemma":[0.9965935,0.0003362868,0.00008069062,0.002893168,0.00004907975,0.00004726767],"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":[0.00003537133,0.0003006503,0.3432048,0.0003531154,0.0001113931,0.00000121656,0.0007229483,0.0009912702,0.001885697,0.4076539,0.04173058,0.2030091],"study_design_scores_gemma":[0.0002486398,0.00001830574,0.00994353,0.000004077832,0.000009057314,0.000002245335,0.00004052458,0.9461269,0.00002222007,0.0004700563,0.04302989,0.00008451261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01233553,0.00008155032,0.985531,0.0008742174,0.0001238464,0.0001814873,0.0001772802,0.00009418394,0.0006009557],"genre_scores_gemma":[0.681378,0.00003152061,0.3135694,0.0002606242,0.00004994675,0.000002369445,0.003663577,0.000007383611,0.001037187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9451357,"threshold_uncertainty_score":0.304755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1126477890387248,"score_gpt":0.3516509776899865,"score_spread":0.2390031886512617,"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."}}