{"id":"W4389265213","doi":"10.1002/jad.12280","title":"Comparing the reliability and validity of youth‐reported checklists and standardized interviews for categorical measurement of emotional and behavioral problems","year":2023,"lang":"en","type":"article","venue":"Journal of Adolescence","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton Health Sciences; McMaster Children's Hospital","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Psychology; Categorical variable; Reliability (semiconductor); Test validity; Psychometrics; Validity; Clinical psychology; Developmental psychology; Applied psychology; Social psychology; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002062145,0.0001022033,0.0003414604,0.00005941955,0.00007978021,0.00001483462,0.00009100488,0.00004864961,0.000007090101],"category_scores_gemma":[0.00008647532,0.00006787913,0.00009073928,0.0001195012,0.0001846224,0.00005629925,0.00005231757,0.0001589863,2.035148e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003341389,"about_ca_system_score_gemma":0.00006157263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002434828,"about_ca_topic_score_gemma":0.00001081506,"domain_scores_codex":[0.9985495,0.0001060541,0.0006834206,0.0001545801,0.0003752605,0.0001311747],"domain_scores_gemma":[0.9989173,0.00004944032,0.0004775376,0.00008939308,0.0003887266,0.00007753753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007530892,0.0007703967,0.975774,0.000800844,0.0001339224,0.000005318801,0.008529147,0.00002335557,0.003000562,0.0005647768,0.001886196,0.007758371],"study_design_scores_gemma":[0.001280443,0.0001977896,0.9954979,0.0005531455,0.00006868442,0.00003934762,0.0008130968,0.000038905,0.0001406668,0.001108638,0.0001892294,0.00007218332],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970655,0.0004271686,0.001096841,0.0006937983,0.000405416,0.0002470954,0.00002154194,0.000005339249,0.00003728097],"genre_scores_gemma":[0.9994924,0.000229874,0.0001502411,0.0000221715,0.00007742496,0.000002216487,0.00000331039,0.00000532654,0.00001703444],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01972385,"threshold_uncertainty_score":0.276803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1750240190954241,"score_gpt":0.3552990267796993,"score_spread":0.1802750076842752,"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."}}