{"id":"W4412694376","doi":"10.1016/j.infbeh.2025.102110","title":"Development and validation of the NIH Baby Toolbox Social-Emotional Functioning measures","year":2025,"lang":"en","type":"article","venue":"Infant Behavior and Development","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; NIH Blueprint for Neuroscience Research; National Institute of Child Health and Human Development; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Psychology; Developmental psychology; Irritability; Conceptualization; Clinical psychology; Construct validity; Construct (python library); Toolbox; Early childhood; Checklist; Anxiety; Psychometrics; Cognitive psychology; Psychiatry","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":[0.0002949881,0.0001780734,0.0001922322,0.0001101505,0.0006456382,0.00004242009,0.0001042403,0.0001054058,0.0001314821],"category_scores_gemma":[0.00001126688,0.0001370124,0.00004439401,0.0001887515,0.0001023925,0.00005969187,0.00009433317,0.0001352713,0.00001003555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006884398,"about_ca_system_score_gemma":0.0002522327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001928071,"about_ca_topic_score_gemma":0.00001649353,"domain_scores_codex":[0.9986565,0.00004979044,0.0004732531,0.0003038424,0.0003056338,0.0002110202],"domain_scores_gemma":[0.9996079,0.00002699225,0.0001183824,0.00009533487,0.0001007436,0.0000506578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008530982,0.0004697641,0.5993457,0.00009769167,0.0001992753,0.000002564381,0.01294421,0.000001473998,0.001422787,0.01492805,0.003709652,0.3667935],"study_design_scores_gemma":[0.000552052,0.00000554654,0.8935338,0.0001333683,0.00002556893,0.000006214595,0.0006317118,2.314672e-7,0.003289163,0.00009278567,0.1015721,0.0001574735],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913415,0.0002943178,0.0004369165,0.0005726895,0.001155741,0.0003130016,0.000006997853,0.00003157152,0.00584728],"genre_scores_gemma":[0.995289,0.00001500285,0.001205934,0.0003826268,0.00005505485,0.00007777964,0.00003492136,0.000008575358,0.002931056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.366636,"threshold_uncertainty_score":0.5587204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03524867994014801,"score_gpt":0.2911082663772443,"score_spread":0.2558595864370963,"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."}}