{"id":"W2907883156","doi":"10.1109/icbk.2018.00054","title":"Principal Sample Analysis for Data Reduction","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dimensionality reduction; Computer science; Reduction (mathematics); Discriminative model; Sample (material); Principal component analysis; Data reduction; Artificial intelligence; MNIST database; Data mining; Pattern recognition (psychology); Generalizability theory; Preprocessor; Sample size determination; Population; Machine learning; Statistics; Mathematics; Artificial neural network","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":[0.0003201519,0.0000386945,0.00006269237,0.00007581999,0.0001158774,0.00007651004,0.0007456211,0.00001653167,0.00007015098],"category_scores_gemma":[0.0001101713,0.00003114191,0.00002942818,0.0004200146,0.00001712939,0.0002219373,0.0002721944,0.0000214525,0.00003475777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005865246,"about_ca_system_score_gemma":0.00001599313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004974092,"about_ca_topic_score_gemma":0.0001127814,"domain_scores_codex":[0.9994308,0.00001728409,0.00007563388,0.0002835031,0.00007943383,0.0001132977],"domain_scores_gemma":[0.998944,0.00004219345,0.0000276088,0.0009063467,0.0000465296,0.00003331547],"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":[0.00002551525,0.0001606285,0.01635399,0.00002214532,0.0006324485,5.632766e-7,0.001442586,0.0009725534,0.0004212396,0.210796,0.06134986,0.7078225],"study_design_scores_gemma":[0.0000688261,0.00004759272,0.002925843,5.797511e-7,0.00002754772,0.000001183211,0.000005410008,0.8567358,0.0001443068,0.001080179,0.1389094,0.00005326493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006895583,0.000004069394,0.989082,0.0009160229,0.0001797414,0.00004032132,0.000003850625,0.0001281637,0.002750238],"genre_scores_gemma":[0.5374406,7.273904e-7,0.4597506,0.00008734586,0.0002344286,0.000002718796,0.00004397689,0.000002013212,0.002437619],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8557633,"threshold_uncertainty_score":0.1385562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06993294597854288,"score_gpt":0.3436422628736149,"score_spread":0.273709316895072,"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."}}