{"id":"W4413165906","doi":"10.1080/10618600.2025.2541012","title":"Boosting Prediction with Data Missing Not at Random","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Boosting (machine learning); Missing data; Computer science; Artificial intelligence; Random forest; Machine learning; Econometrics; Statistics; Data mining; 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":[0.0003018489,0.00006999944,0.0001395926,0.000124109,0.0001992448,0.0001221401,0.00022127,0.00003182166,0.00000426701],"category_scores_gemma":[0.0001364819,0.00004952906,0.00001731073,0.0001973337,0.00006174167,0.0003451372,0.0001370541,0.0001402775,7.559782e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001225992,"about_ca_system_score_gemma":0.00007980321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002272903,"about_ca_topic_score_gemma":0.000001807863,"domain_scores_codex":[0.9990852,0.00005469123,0.0003155278,0.0001373856,0.0003201404,0.00008699774],"domain_scores_gemma":[0.9987224,0.0006537548,0.0001879874,0.00009355915,0.0002678564,0.00007448954],"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":[0.002228859,0.0004835083,0.02855713,0.0003346443,0.0005576431,0.000355393,0.0005714449,0.0346511,0.001004023,0.1765171,0.090121,0.6646182],"study_design_scores_gemma":[0.002375863,0.0001850389,0.03986236,0.0002852513,0.00005406047,0.0002339308,0.00001358427,0.7685364,0.00007249449,0.1854507,0.002827227,0.0001029753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0180476,0.0001194994,0.9790686,0.002410092,0.0001508804,0.00004026561,0.00006998729,0.00001114144,0.00008196385],"genre_scores_gemma":[0.5380728,0.00005923009,0.4610327,0.0006715052,0.00006009073,6.343085e-7,0.00005885494,0.000003331863,0.00004083159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7338853,"threshold_uncertainty_score":0.2019736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02070957838485018,"score_gpt":0.2705212398444851,"score_spread":0.2498116614596349,"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."}}