{"id":"W106071789","doi":"10.4018/978-1-60566-010-3.ch082","title":"Data Mining with Incomplete Data","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Missing data; Data mining; Ambiguity; Computer science; Survey data collection; Data set; Set (abstract data type); Data science; Knowledge extraction; Statistics; Artificial intelligence; Machine learning; 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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0002409715,0.0004180256,0.0003994567,0.00005502269,0.0001901575,0.0004960411,0.01108941,0.0001732535,0.000007985012],"category_scores_gemma":[0.00001336524,0.0003716473,0.00003236425,0.00004840133,0.0001080044,0.0004786584,0.005618244,0.0002607044,0.0001774559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006453912,"about_ca_system_score_gemma":0.0003613879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006778027,"about_ca_topic_score_gemma":0.0001823954,"domain_scores_codex":[0.9970695,0.00001163953,0.0003647428,0.00165981,0.0005241025,0.0003702166],"domain_scores_gemma":[0.9896562,0.00004609752,0.0002816841,0.009750761,0.00007585598,0.0001894267],"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":[0.000002124214,0.000006423448,0.000001137262,0.000005173821,0.00003895671,0.00004886862,0.00001016126,6.15564e-7,5.448425e-7,0.6246581,0.02825587,0.346972],"study_design_scores_gemma":[0.0002569916,0.0000997313,0.00002897112,0.0002513175,0.00007343197,0.0001943058,0.00000389005,0.0199401,0.000001007575,0.05861969,0.9198899,0.0006406866],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.000001755712,0.0002123563,0.1187711,0.0003118326,0.0001328889,0.0002359333,0.007753318,0.000303989,0.8722768],"genre_scores_gemma":[0.0006053334,0.00001374377,0.9315026,0.001618003,0.0006686387,0.00001184097,0.002562843,0.00006069761,0.06295633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.891634,"threshold_uncertainty_score":0.9998735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07953766576169785,"score_gpt":0.2923643524653435,"score_spread":0.2128266867036457,"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."}}