{"id":"W4402390737","doi":"10.23889/ijpds.v9i5.2518","title":"Leveraging Machine Learning to Combat Missingness and Error in Data","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Victoria Park","funders":"","keywords":"Missing data; Computer science; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07188791,0.002201668,0.002083408,0.003754005,0.002143043,0.004765069,0.003923905,0.002687745,0.001614801],"category_scores_gemma":[0.1670211,0.001057798,0.001628396,0.003667367,0.002456981,0.006615834,0.004239505,0.004496796,0.001071418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002091806,"about_ca_system_score_gemma":0.003945429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006273272,"about_ca_topic_score_gemma":0.005966423,"domain_scores_codex":[0.964779,0.01914574,0.003536152,0.005977329,0.005543152,0.00101867],"domain_scores_gemma":[0.813381,0.1231084,0.01671244,0.03197842,0.01352985,0.00128984],"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":[0.0005349236,0.0007931414,0.1771235,0.0007667226,0.001201242,0.0007071043,0.001717064,0.3697658,0.005087957,0.01380172,0.006626284,0.4218745],"study_design_scores_gemma":[0.00004808509,0.0003388499,0.01090093,0.0002710306,0.0001456908,0.0002950306,0.0005043245,0.9353401,0.009530745,0.03749841,0.005035008,0.00009178176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06987429,0.0006101572,0.9214705,0.002759156,0.0001593081,0.0002381652,0.0004104152,0.003408449,0.001069586],"genre_scores_gemma":[0.6566009,0.0002446529,0.33954,0.0007440151,0.0001431636,0.0002613491,0.0009743643,0.000242982,0.001248686],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07188791,"threshold_uncertainty_score":0.3801842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1132270631980558,"score_gpt":0.4198903725605341,"score_spread":0.3066633093624783,"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."}}