{"id":"W1987787956","doi":"10.1145/1281192.1281294","title":"Cleaning disguised missing data","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Missing data; Outlier; Anomaly detection; Computer science; Data mining; Data quality; Anomaly (physics); Statistics; Artificial intelligence; Mathematics; Machine learning; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.000476687,0.00004617703,0.00004423049,0.0000300967,0.0001191043,0.000169809,0.001578574,0.0000152894,0.00001465752],"category_scores_gemma":[0.00003384468,0.00004004705,0.000008344291,0.0002239492,0.00001461759,0.0005087659,0.0006826128,0.00004742685,0.00008050973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007400387,"about_ca_system_score_gemma":0.00001858639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003266996,"about_ca_topic_score_gemma":0.000008783695,"domain_scores_codex":[0.9993284,0.000004344561,0.0001133444,0.0002835287,0.000105325,0.0001650932],"domain_scores_gemma":[0.9985551,0.00006967256,0.00002675668,0.00126275,0.00001653834,0.00006924072],"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":[2.244005e-7,0.00001584568,0.0000735961,9.004484e-7,0.000002055458,0.000003469549,0.00006418243,6.594563e-7,0.0003546838,0.05225283,0.00687506,0.9403565],"study_design_scores_gemma":[0.0001872951,0.00001436254,0.006385021,0.00001382402,0.00000388651,0.0000188069,0.0001011036,0.7079058,0.001926028,0.002524422,0.2806949,0.0002245438],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003596159,0.00001788651,0.9711591,0.000944138,0.00007966962,0.00002989479,0.000004507172,0.0001927176,0.02721249],"genre_scores_gemma":[0.06199469,0.000001651947,0.9370093,0.0004003514,0.00008059858,6.483858e-7,0.00003349364,0.00000398361,0.0004752611],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.940132,"threshold_uncertainty_score":0.2933409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06706517474363113,"score_gpt":0.3292222302198833,"score_spread":0.2621570554762522,"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."}}