{"id":"W4242580366","doi":"10.4018/978-1-59904-951-9.ch193","title":"Data Mining with Incomplete Data","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Missing data; Ambiguity; Survey data collection; Data mining; Computer science; Data science; Data set; Mathematics; Artificial intelligence; Statistics; Machine learning","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0001738524,0.0004192123,0.0004046171,0.00005536186,0.000253559,0.0003177112,0.01093142,0.0001732094,0.000008247127],"category_scores_gemma":[0.00001427283,0.0003742493,0.00003392423,0.0000488713,0.000176057,0.0004734163,0.008010593,0.0002644567,0.0002281342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006486427,"about_ca_system_score_gemma":0.0004612892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001070821,"about_ca_topic_score_gemma":0.0001785609,"domain_scores_codex":[0.997017,0.00001169564,0.0003686947,0.001677864,0.0005565954,0.0003682059],"domain_scores_gemma":[0.9895262,0.00005598421,0.0002842321,0.009858762,0.0000820615,0.0001927356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003578512,0.00001036462,0.000004341906,0.00001085897,0.00008998504,0.0001543335,0.00003513803,0.000001074894,6.560992e-7,0.6832873,0.139453,0.1769493],"study_design_scores_gemma":[0.0002507271,0.00006385767,0.00002316408,0.0001890035,0.00005178219,0.0004788023,0.000003984865,0.01878664,9.342314e-7,0.008893013,0.9706572,0.0006008428],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.00000380662,0.0003206636,0.1229648,0.0001856487,0.0001829263,0.0002450116,0.01085384,0.0003126675,0.8649307],"genre_scores_gemma":[0.0008343218,0.00005203111,0.9394673,0.001108291,0.0007465531,0.00002153807,0.003015987,0.00008895421,0.0546651],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8312042,"threshold_uncertainty_score":0.999871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09424581898306579,"score_gpt":0.2878700833209476,"score_spread":0.1936242643378818,"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."}}