{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06206858,0.0003736218,0.002789898,0.0005017995,0.000633337,0.00122122,0.001820458,0.0001910996,0.01559624],"category_scores_gemma":[0.001431802,0.0001690588,0.0007668999,0.001986022,0.0008072061,0.0003870495,0.0003276218,0.0004526056,0.00002286171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002550795,"about_ca_system_score_gemma":0.0001996992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001440496,"about_ca_topic_score_gemma":0.0000510757,"domain_scores_codex":[0.9790601,0.007099221,0.004328649,0.001616146,0.007526585,0.0003693057],"domain_scores_gemma":[0.9915737,0.001541721,0.004496066,0.001707929,0.0005931578,0.00008742467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003870397,0.00004505047,0.06269183,0.00006537993,0.00002115872,0.00001530012,0.0006501505,0.00001450494,0.00005549981,0.00004457153,0.9327519,0.003640782],"study_design_scores_gemma":[0.0003207185,0.0005379833,0.005863962,0.00008423337,0.0006307838,0.0001091997,0.006411494,0.0007140412,0.0001341927,0.002895927,0.9816278,0.0006697219],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7882954,0.0006532968,0.001213077,0.2068048,0.0004165669,0.0009230364,0.0004890301,0.00001107729,0.001193707],"genre_scores_gemma":[0.562286,0.00005116471,0.05754751,0.3579457,0.001402926,0.0004408785,0.0005661021,0.00008853729,0.01967116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2260094,"threshold_uncertainty_score":0.9998156,"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."}}