{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01608617,0.000828822,0.0008649193,0.002354075,0.0008414953,0.001055056,0.001729252,0.0008004382,0.002895151],"category_scores_gemma":[0.018063,0.000521934,0.001430924,0.00101475,0.0006209985,0.001223381,0.002270705,0.001091212,0.00176776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001287875,"about_ca_system_score_gemma":0.004477976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00951718,"about_ca_topic_score_gemma":0.01849603,"domain_scores_codex":[0.9918682,0.002648961,0.001406123,0.0006222163,0.002998067,0.0004564397],"domain_scores_gemma":[0.9834719,0.003603411,0.00134314,0.001571756,0.009345707,0.0006641382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001627389,0.002642582,0.6285648,0.0004795154,0.0003075784,0.0003326687,0.002982523,0.003176475,0.01965714,0.004211016,0.01198211,0.3240362],"study_design_scores_gemma":[0.0002034487,0.002146896,0.9512533,0.0001917507,0.0001670995,0.0006970876,0.001049945,0.005587494,0.01882891,0.00114398,0.01863515,0.00009497248],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9020229,0.0007930343,0.04663033,0.0007961632,0.0003888881,0.01022586,0.008969257,0.0007692498,0.02940433],"genre_scores_gemma":[0.7945081,0.000752567,0.1458189,0.0005465046,0.0001020529,0.02394338,0.01886299,0.0004862372,0.01497915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01608617,"threshold_uncertainty_score":0.08507288,"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."}}