{"id":"W2273367618","doi":"10.6000/2292-2598.2015.03.04.2","title":"Utility and Validity of Authentic Assessments and Conventional Tests for International Early Childhood Intervention Purposes: Evidence from U.S. National Social Validity Research","year":2016,"lang":"en","type":"article","venue":"Journal of Intellectual Disability - Diagnosis and Treatment","topic":"Early Childhood Education and Development","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Intervention (counseling); External validity; Test validity; Criterion validity; Internal validity; Applied psychology; Construct validity; Clinical psychology; Social psychology; Psychometrics; Statistics; Mathematics; Psychiatry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002818073,0.0001379057,0.0002901939,0.0001133899,0.0004002182,0.0001408965,0.0001540017,0.00009259435,0.0005284378],"category_scores_gemma":[0.008764486,0.0000978069,0.0001724956,0.0001191431,0.0008546829,0.0004922043,0.00008290113,0.0001045957,0.000002026776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004832809,"about_ca_system_score_gemma":0.0004951854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007868031,"about_ca_topic_score_gemma":0.0006802542,"domain_scores_codex":[0.9973791,0.0006611758,0.0006396354,0.0003008044,0.0008235556,0.0001956881],"domain_scores_gemma":[0.9915754,0.006647039,0.0003224379,0.00007558813,0.001207791,0.0001717367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001676802,0.002196825,0.9070407,0.0000180327,0.000238348,3.738195e-7,0.01775051,5.5357e-8,0.00002551116,0.001071408,0.00111126,0.07037927],"study_design_scores_gemma":[0.001197143,0.0008323676,0.9716931,0.0002848952,0.00006062488,0.000001667962,0.002374707,0.000005077628,0.0003827257,0.02161013,0.001463674,0.00009386685],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994399,0.0003245007,0.0003070179,0.003809199,0.000408444,0.0004871795,0.0001639187,0.000006274454,0.00009443432],"genre_scores_gemma":[0.9967521,0.002155934,0.0006126494,0.00001690063,0.0003209985,0.0000622005,0.000009169014,0.00000624019,0.00006379153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0702854,"threshold_uncertainty_score":0.9995851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2696021189989222,"score_gpt":0.4676630951801826,"score_spread":0.1980609761812603,"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."}}