{"id":"W1969168383","doi":"10.1198/016214506000000447","title":"Evaluating Kindergarten Retention Policy","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"School Choice and Performance","field":"Social Sciences","cited_by":377,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grade retention; Propensity score matching; Retention rate; Psychology; Covariate; Multilevel model; Average treatment effect; Affect (linguistics); Developmental psychology; Demography; Mathematics; Econometrics; Academic achievement; Statistics; Computer science; Sociology","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":[0.002213277,0.00005121353,0.00014882,0.00006029631,0.0003476628,0.00007797641,0.0001817785,0.00003036454,0.00004891478],"category_scores_gemma":[0.004355938,0.00003684037,0.00008338949,0.0004783094,0.0001019834,0.000196815,0.00001594634,0.0002058638,0.00001690203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008488031,"about_ca_system_score_gemma":0.0003904279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003804612,"about_ca_topic_score_gemma":0.0007604581,"domain_scores_codex":[0.9978979,0.0005266496,0.00032859,0.00005989055,0.0009553787,0.0002316322],"domain_scores_gemma":[0.9976632,0.0005766213,0.001291866,0.0000642911,0.0003473966,0.00005661351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001232977,0.0001517692,0.7617533,0.000008758769,0.0001003859,0.000004317278,0.00149966,0.0006368816,0.002060644,0.04939521,0.09973516,0.08453063],"study_design_scores_gemma":[0.0002435712,0.0001201479,0.9587475,0.00001786359,0.00005791975,0.000002262637,0.0004897214,0.0002899808,0.00003791819,0.0264672,0.01345234,0.00007354662],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9637054,0.00002932371,0.003443901,0.0232635,0.0005213329,0.00009275728,0.0000162198,0.00001530988,0.008912315],"genre_scores_gemma":[0.992539,0.00002841788,0.002955765,0.0004628896,0.002429113,0.000001072761,0.000001385939,0.000005275373,0.001577119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1969942,"threshold_uncertainty_score":0.5751461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03241118186837891,"score_gpt":0.3965013558341809,"score_spread":0.364090173965802,"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."}}