{"id":"W2054521721","doi":"10.1007/s10115-009-0245-8","title":"Mining incomplete survey data through classification","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Data mining; Computer science; Classifier (UML); Complete information; Data set; Artificial intelligence; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003440158,0.0007899865,0.00235631,0.007087081,0.001083543,0.003342159,0.002276636,0.001400022,0.002261367],"category_scores_gemma":[0.01486697,0.0005808569,0.001755656,0.008942463,0.0009063632,0.003880474,0.001962285,0.001418873,0.001828069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003916,"about_ca_system_score_gemma":0.001838106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005739502,"about_ca_topic_score_gemma":0.007566735,"domain_scores_codex":[0.996483,0.001098482,0.0003177076,0.0007633005,0.0009849096,0.0003526021],"domain_scores_gemma":[0.9875729,0.006105102,0.001292381,0.002863755,0.001914943,0.0002508566],"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":[0.0003127668,0.0004290742,0.08690983,0.0004654329,0.0003228158,0.0002360258,0.0005261197,0.02553726,0.002790309,0.01435305,0.01278264,0.8553346],"study_design_scores_gemma":[0.00005105343,0.0001554727,0.01921575,0.0001962824,0.000346468,0.0005779616,0.0009903309,0.871932,0.006831903,0.08171186,0.01792961,0.00006118715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09135821,0.001761642,0.8978154,0.001083748,0.00014716,0.0003576363,0.002508975,0.001721293,0.003245887],"genre_scores_gemma":[0.6101188,0.001398525,0.3744561,0.0003393726,0.0003208993,0.0005120386,0.008116314,0.0001138893,0.004624099],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007087081,"threshold_uncertainty_score":0.01819348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1156448316538467,"score_gpt":0.3234492842129648,"score_spread":0.2078044525591181,"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."}}