{"id":"W2071767222","doi":"10.1080/08839510902872223","title":"AN EMPIRICAL COMPARISON OF TECHNIQUES FOR HANDLING INCOMPLETE DATA USING DECISION TREES","year":2009,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":152,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Society of Intestinal Research","funders":"","keywords":"Missing data; Imputation (statistics); Computer science; Spurious relationship; Decision tree; Robustness (evolution); Data mining; Decision tree learning; Machine learning; Statistics; Artificial intelligence; 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":[0.0008480494,0.0001699366,0.0004700278,0.00009040788,0.0001512728,0.00006442337,0.0006594223,0.0001102512,0.00003379781],"category_scores_gemma":[0.0009807795,0.0001486439,0.00004402104,0.0002204157,0.0001317338,0.0001060758,0.00008495722,0.0001374263,0.000002984628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002188262,"about_ca_system_score_gemma":0.00004203472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001435365,"about_ca_topic_score_gemma":0.00003586833,"domain_scores_codex":[0.9981696,0.00005201986,0.0008399711,0.0004341296,0.000247736,0.0002565524],"domain_scores_gemma":[0.9965889,0.002229247,0.0002323311,0.0007418645,0.0001192103,0.00008847474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001032196,0.0002224878,0.00003803974,0.00001423579,0.000004260331,3.584443e-7,0.0001948315,0.00001650092,0.02978529,0.3747581,0.00004829403,0.5948144],"study_design_scores_gemma":[0.00001414452,0.0001682226,0.00003057691,0.00004727083,0.00002646124,7.01557e-7,0.0001900351,0.1746153,0.1721168,0.6526097,0.00005784584,0.0001230144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01956676,0.00001442151,0.9795231,0.00003987926,0.0000564511,0.0004288448,0.00007049554,0.0000800433,0.0002200076],"genre_scores_gemma":[0.4775666,0.000001313768,0.5223025,0.00003135658,0.00007404022,0.000005316435,0.0000103197,0.000008251412,2.456577e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5946914,"threshold_uncertainty_score":0.6061522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4797650739687325,"score_gpt":0.5540475740189142,"score_spread":0.07428250005018178,"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."}}