{"id":"W2094656673","doi":"10.5430/air.v4n1p22","title":"Diagnostic with incomplete nominal/discrete data","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Missing data; Computer science; Imputation (statistics); Data mining; Decision tree; Cartesian product; Machine learning; Bayesian probability; Naive Bayes classifier; Outcome (game theory); Artificial intelligence; Mathematics; Support vector machine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004316865,0.0001629307,0.0001869193,0.0003459394,0.000256801,0.0006022323,0.005798282,0.00007374032,0.00002779138],"category_scores_gemma":[0.003351089,0.0001350484,0.00001928395,0.001701476,0.0005227103,0.001543312,0.002380411,0.0005044767,0.001482433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001459424,"about_ca_system_score_gemma":0.000582066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006415021,"about_ca_topic_score_gemma":0.000418679,"domain_scores_codex":[0.9962105,0.0004064429,0.0004045714,0.0009417905,0.001317092,0.0007195882],"domain_scores_gemma":[0.9937494,0.001332377,0.00008517733,0.003635902,0.0008414316,0.0003557095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007401031,0.0002090369,0.0008668441,0.00002090559,0.00002220334,0.0001419777,0.001067603,0.0001028443,0.001963144,0.6338836,0.01565101,0.3459968],"study_design_scores_gemma":[0.0001078025,0.001351536,0.0009751762,0.0001871915,0.00001128642,0.000105468,0.002094513,0.3844694,0.148017,0.3900749,0.07167052,0.0009352731],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002608278,0.00009440047,0.9893603,0.004620686,0.0001211197,0.0004774461,0.00003571852,0.0003208018,0.002361219],"genre_scores_gemma":[0.8840889,0.00004018889,0.1153084,0.00009601397,0.000160751,0.00009633878,0.00008101486,0.00002033463,0.0001079924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8814806,"threshold_uncertainty_score":0.9995808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5670274782417085,"score_gpt":0.4842737624100367,"score_spread":0.08275371583167185,"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."}}