{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007624028,0.00009261708,0.0001238873,0.00007432222,0.0001999102,0.0005544264,0.000829316,0.00004717922,0.000001006363],"category_scores_gemma":[0.00006347284,0.00008305009,0.000009601961,0.0003940124,0.00001848562,0.007777039,0.0002056111,0.00005653798,0.0001853119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001802283,"about_ca_system_score_gemma":0.00004826876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006196569,"about_ca_topic_score_gemma":0.000006809192,"domain_scores_codex":[0.9990896,0.00006294285,0.0003867131,0.0001939751,0.0001305095,0.0001362891],"domain_scores_gemma":[0.9986237,0.00008506371,0.0001654651,0.000908927,0.0001625666,0.00005431762],"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":[0.000002803406,0.00005365647,0.0007877338,0.00004946192,0.00001433126,2.013147e-7,0.00693646,0.000009888283,0.00004569829,0.2516141,0.07221185,0.6682739],"study_design_scores_gemma":[0.0001501913,0.00002695558,0.03488784,0.00002730307,0.000002264198,0.00001111608,0.0002162296,0.5417486,0.000006978911,0.00006968384,0.4227348,0.0001180137],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001922861,0.0005102273,0.9511836,0.0003523874,0.0003901738,0.0002584386,0.0001457503,0.0001982892,0.04503833],"genre_scores_gemma":[0.9741927,0.0001107316,0.02353493,0.0002604011,0.0001259238,0.00002167201,0.001589936,0.000003533229,0.0001601601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9722698,"threshold_uncertainty_score":0.5638165,"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."}}