{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8819278,0.004933863,0.01315767,0.02330633,0.01697509,0.0384502,0.01605861,0.008299793,0.002846929],"category_scores_gemma":[0.8914865,0.005631053,0.006914468,0.02685083,0.07540442,0.04503667,0.03353306,0.02447964,0.0009778249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.04592519,"about_ca_system_score_gemma":0.1197961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04194655,"about_ca_topic_score_gemma":0.04222233,"domain_scores_codex":[0.1229431,0.7276754,0.07307808,0.01739492,0.0556481,0.003260401],"domain_scores_gemma":[0.0292924,0.8071167,0.01973854,0.06616147,0.07463354,0.003057445],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004496052,0.0009459141,0.07672139,0.0279,0.002930654,0.0005134613,0.120245,0.003742605,0.0009588266,0.2758256,0.01541807,0.4743489],"study_design_scores_gemma":[0.0005665596,0.001310827,0.05232512,0.103563,0.001898676,0.0006814155,0.09101199,0.02235701,0.003070713,0.6459905,0.07611197,0.001112148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03133917,0.05468802,0.6475493,0.2222441,0.006070459,0.0151668,0.0006189222,0.001444138,0.02087913],"genre_scores_gemma":[0.2827574,0.008471387,0.6654702,0.01300406,0.001017418,0.02767684,0.0004541278,0.0004153478,0.0007333118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1180722,"threshold_uncertainty_score":0.3332121,"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."}}