{"id":"W3135512811","doi":"10.15626/mp.2019.1645","title":"The Validation Crisis in Psychology","year":2021,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; University of Toronto Mississauga; University of Toronto","keywords":"Nomological network; Construct (python library); Construct validity; Cronbach's alpha; Psychology; Criterion validity; External validity; Metatheory; Predictive validity; Incremental validity; Psychometrics; Structural equation modeling; Social psychology; Computer science; Developmental psychology; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00268299,0.0002732209,0.000600559,0.0002567616,0.0002463453,0.0000464754,0.0007062502,0.0003985816,0.01260069],"category_scores_gemma":[0.0003163026,0.0002060631,0.000238379,0.0009354934,0.0002432322,0.00008549315,0.0001422984,0.0009088328,0.003012215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006502139,"about_ca_system_score_gemma":0.00008001326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001413965,"about_ca_topic_score_gemma":0.000461715,"domain_scores_codex":[0.9935184,0.003061426,0.0008945133,0.001031356,0.0003631493,0.001131205],"domain_scores_gemma":[0.9969552,0.0006096183,0.0001838156,0.00189002,0.000158655,0.0002027408],"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":[0.000752087,0.00170711,0.01309052,0.0000481255,0.001651534,0.001289769,0.001497832,0.000003218763,0.001660726,0.04383012,0.6127722,0.3216968],"study_design_scores_gemma":[0.001739493,0.0002286281,0.1052832,0.000003240993,0.0001296941,0.000268319,0.0003044461,0.000003977334,0.0003047508,0.01810754,0.8734129,0.0002138094],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1573514,0.04168805,0.00397775,0.3177763,0.01597501,0.001923883,0.00007296463,0.000275213,0.4609595],"genre_scores_gemma":[0.8507349,0.006304145,0.0038998,0.1071386,0.001162129,0.00262625,0.0002032004,0.0002006988,0.02773028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6933835,"threshold_uncertainty_score":0.9977641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3490952054780505,"score_gpt":0.5715458269845495,"score_spread":0.222450621506499,"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."}}