{"id":"W2004753031","doi":"10.1117/12.542509","title":"Experimental analysis of methods for imputation of missing values in databases","year":2004,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Imputation (statistics); Missing data; Computer science; Data mining; Decision tree; Naive Bayes classifier; Machine learning; Algorithm; Support vector machine","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":[0.0008661589,0.0001727829,0.0004343385,0.0002433551,0.00004613531,0.00005561505,0.000992418,0.00006890963,0.000001646926],"category_scores_gemma":[0.0004322977,0.0001540318,0.0004750574,0.0009073417,0.0001441808,0.0006988621,0.0001979881,0.0001000755,7.83385e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001019467,"about_ca_system_score_gemma":0.00004336026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004121462,"about_ca_topic_score_gemma":1.504563e-7,"domain_scores_codex":[0.9983983,2.611657e-8,0.0007235445,0.0003417541,0.0003234833,0.0002128669],"domain_scores_gemma":[0.998253,0.000251693,0.0004796149,0.00008424225,0.0008737359,0.00005771689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001694346,0.0001845442,0.00008281881,0.0001552438,0.0003931836,1.241608e-8,0.000496931,0.0009528968,0.5192831,0.4751884,0.00006745143,0.003178476],"study_design_scores_gemma":[0.0006880857,0.0001718967,0.0008939542,0.0001717971,0.0002088106,0.000002351197,0.0009443866,0.383387,0.6098325,0.003385325,0.0001505763,0.0001633203],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8835726,0.0001267711,0.1150785,0.0006027703,0.00006563999,0.0003236365,0.00009206344,0.00002827398,0.0001096647],"genre_scores_gemma":[0.1841291,0.00001634671,0.8156601,0.00001945688,0.000042081,0.00009239445,0.00002065312,0.00001383414,0.000006032359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7005816,"threshold_uncertainty_score":0.6281236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02778216031126049,"score_gpt":0.3287805926909821,"score_spread":0.3009984323797216,"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."}}