{"id":"W4407775247","doi":"10.1017/ehs.2025.3","title":"Construct validity in cross-cultural, developmental research: challenges and strategies for improvement","year":2025,"lang":"en","type":"article","venue":"Evolutionary Human Sciences","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Economic and Social Research Council","keywords":"Construct validity; Construct (python library); Psychology; External validity; Computer science; Developmental psychology; Social psychology; Psychometrics","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01138155,0.0001142822,0.0001745174,0.0005983365,0.001486385,0.0007035643,0.0006164002,0.00005458379,0.0002496425],"category_scores_gemma":[0.0007751474,0.00008116222,0.00003876143,0.0007610813,0.002097644,0.00171623,0.0002437329,0.000131968,0.00001948163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001778508,"about_ca_system_score_gemma":0.001123877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000406325,"about_ca_topic_score_gemma":0.0005945861,"domain_scores_codex":[0.9967389,0.0002290807,0.0005486843,0.0006163415,0.001506099,0.0003609165],"domain_scores_gemma":[0.9979282,0.001088299,0.00009864555,0.0001584601,0.0006701416,0.00005624819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0000365938,0.0001311335,0.1029834,0.00004116567,0.00001087315,0.000001267724,0.003960249,0.0002315717,0.002272221,0.8451395,0.01158025,0.03361181],"study_design_scores_gemma":[0.0004768791,0.0002322929,0.487073,0.00003647629,0.000001413482,0.000002729618,0.04232751,0.001602402,0.0001688749,0.454338,0.01362241,0.000117998],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9333614,0.001307247,0.00007898975,0.00216857,0.0002691385,0.0004266853,0.00001079758,0.00001854959,0.06235859],"genre_scores_gemma":[0.9955984,0.0002311383,0.002385016,0.00009701811,0.00003979982,0.0001157494,0.000003584837,0.000001908681,0.00152742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3908015,"threshold_uncertainty_score":0.9998136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6656248021872823,"score_gpt":0.6127833348367184,"score_spread":0.05284146735056383,"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."}}