{"id":"W4406051520","doi":"10.1027/1015-5759/a000877","title":"Cracks, Gaps, and Holes in Validation Practice as Evidenced From a Validation Synthesis of the English Version of the Rosenberg Self-Esteem Scale","year":2024,"lang":"en","type":"article","venue":"European Journal of Psychological Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Scale (ratio); Self-esteem; Psychometrics; Test validity; Social psychology; Clinical psychology; Cartography","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5569619,0.0008030472,0.002325199,0.0152549,0.003549729,0.008999966,0.00272952,0.001990456,0.001900722],"category_scores_gemma":[0.6927187,0.001680565,0.00254176,0.01163532,0.008431139,0.01406609,0.01037035,0.002839358,0.0002149123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008337134,"about_ca_system_score_gemma":0.03176087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005669118,"about_ca_topic_score_gemma":0.01243531,"domain_scores_codex":[0.5169646,0.2880088,0.1369617,0.01461894,0.04047233,0.002973623],"domain_scores_gemma":[0.1620479,0.7003647,0.03698251,0.02592407,0.07340924,0.001271533],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0006169723,0.0001430038,0.07832151,0.1020478,0.002271469,0.000943888,0.2837029,0.001022991,0.003019678,0.03952343,0.006266342,0.4821201],"study_design_scores_gemma":[0.0002621363,0.0006878132,0.08333102,0.5326043,0.005844578,0.001364548,0.1912836,0.003802969,0.005814878,0.04776866,0.1268726,0.0003629529],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4076785,0.3474213,0.141703,0.07155204,0.003739361,0.006215399,0.002402815,0.0002438489,0.01904367],"genre_scores_gemma":[0.8780673,0.03595742,0.07111991,0.008150642,0.0003508208,0.00486155,0.0007323785,0.0002009883,0.0005589679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4430381,"threshold_uncertainty_score":0.5463449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1700920110475426,"score_gpt":0.4586256186510765,"score_spread":0.2885336076035339,"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."}}