{"id":"W4220858813","doi":"10.1017/s0140525x21000376","title":"Addressing a crisis of generalizability with large-scale construct validation","year":2022,"lang":"en","type":"letter","venue":"Behavioral and Brain Sciences","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Generalizability theory; Construct (python library); Scale (ratio); Construct validity; Psychology; Computer science; Econometrics; Management science; Psychometrics; Economics; Clinical psychology; Developmental psychology","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":[0.5583432,0.002125708,0.006257804,0.006977421,0.003721663,0.0120696,0.01027438,0.02104633,0.003883425],"category_scores_gemma":[0.8207363,0.001941781,0.005167102,0.004460799,0.02971262,0.02380115,0.01268716,0.04364361,0.002224457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0153847,"about_ca_system_score_gemma":0.02166414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008807153,"about_ca_topic_score_gemma":0.00804461,"domain_scores_codex":[0.4713516,0.3447432,0.07172066,0.0305554,0.07870901,0.002920123],"domain_scores_gemma":[0.07788371,0.8498613,0.01434005,0.02685894,0.02831915,0.002736854],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001146876,0.0002976199,0.01624469,0.01323733,0.002783331,0.002287262,0.007462064,0.00203099,0.001012679,0.1374277,0.4866741,0.3293954],"study_design_scores_gemma":[0.001074268,0.000706819,0.009246485,0.02369248,0.001032842,0.002658636,0.004012271,0.00929135,0.001404367,0.6678013,0.2785229,0.0005563129],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.001551415,0.01140858,0.01534784,0.9611863,0.008258237,0.0002373646,0.0002100381,0.0001577689,0.001642453],"genre_scores_gemma":[0.06623311,0.0110929,0.05383192,0.839964,0.02449775,0.002763642,0.0003607494,0.0002473441,0.00100862],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.4416568,"threshold_uncertainty_score":0.5446415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7390527417927718,"score_gpt":0.5275772326643419,"score_spread":0.2114755091284299,"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."}}