{"id":"W1973009402","doi":"10.1016/j.chemolab.2005.04.008","title":"Variance reduction in estimating classification error using sparse datasets","year":2005,"lang":"en","type":"article","venue":"Chemometrics and Intelligent Laboratory Systems","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Estimator; Statistics; Resampling; Variance (accounting); Mathematics; Jackknife resampling; Sample size determination; Classifier (UML); Mean squared error; Computer science; Pattern recognition (psychology); Artificial intelligence","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":[0.001133682,0.000169565,0.0003099577,0.0003611758,0.00008861662,0.00007703772,0.0001050552,0.0001124059,0.000008899972],"category_scores_gemma":[0.001835438,0.000163303,0.00001902969,0.001249317,0.00006484379,0.0002976434,0.00003979813,0.0001860144,0.000005742645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002126416,"about_ca_system_score_gemma":0.00004587171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001778073,"about_ca_topic_score_gemma":0.000001227018,"domain_scores_codex":[0.99843,0.0001167995,0.0006112455,0.00037114,0.0002281892,0.0002426854],"domain_scores_gemma":[0.9988204,0.0003243445,0.0002743221,0.0003028598,0.0001611328,0.0001169355],"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":[0.00009061216,0.001138484,0.000866584,0.00246939,0.0001080229,0.00003182344,0.00191536,0.03460445,0.04821507,0.7290453,0.002784049,0.1787308],"study_design_scores_gemma":[0.0002020165,0.00003723725,0.00003678281,0.0001973771,0.00002605882,0.00001664061,0.000552041,0.9793661,0.003410083,0.007563506,0.008318663,0.0002734593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05754365,0.0010816,0.9402195,0.00003924936,0.0004896452,0.000334144,0.0001576831,0.00003878869,0.00009571609],"genre_scores_gemma":[0.4686811,0.00007617738,0.530888,0.00001772534,0.0002299755,0.00002192739,0.00002305995,0.00002437763,0.00003772211],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9447617,"threshold_uncertainty_score":0.6659302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2556232352383119,"score_gpt":0.4383509325350697,"score_spread":0.1827276972967578,"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."}}