{"id":"W7084081395","doi":"10.64628/aam.ap6kdpyku","title":"Kindergarten classes are too big for teachers to effectively assess students","year":2019,"lang":"en","type":"article","venue":"","topic":"Economic and Technological Innovation","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Queen's University","funders":"","keywords":"Class (philosophy); Data collection; Work (physics); Measure (data warehouse)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003964935,0.000119732,0.0003075326,0.0002018712,0.00004691444,0.00009601381,0.0003004435,0.0001495482,0.0002571167],"category_scores_gemma":[0.00014463,0.0001241816,0.00007531223,0.0002079851,0.00002170824,0.0001416001,0.00008590815,0.0001004259,0.001614524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001209494,"about_ca_system_score_gemma":0.000006621439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005412802,"about_ca_topic_score_gemma":0.00003213153,"domain_scores_codex":[0.9989707,0.000004836922,0.0003565147,0.0004138124,0.00002286897,0.0002312623],"domain_scores_gemma":[0.9993897,0.00009172025,0.0002007779,0.0002388093,0.00003412563,0.00004485531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009951921,0.00007639867,0.6019983,0.00001143036,0.00004627494,2.204312e-7,0.00002877825,0.00001767581,0.00004871317,0.3915615,0.003376733,0.00282402],"study_design_scores_gemma":[0.001349412,0.0003779664,0.8001359,0.00001511604,0.000004851427,7.430992e-7,0.0004844108,0.0002503867,0.001029855,0.08434431,0.1115637,0.0004433908],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9423048,0.00003010022,0.01870072,0.001406974,0.0004414502,0.0006582782,0.00003565245,0.0001080563,0.03631394],"genre_scores_gemma":[0.989588,0.000003615291,0.001443197,0.001266191,0.00005660285,0.0001309542,0.000009031955,0.00001812523,0.007484335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3072172,"threshold_uncertainty_score":0.9991629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08716888240274955,"score_gpt":0.2806268351910013,"score_spread":0.1934579527882518,"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."}}