{"id":"W4254492958","doi":"10.31234/osf.io/q247m","title":"The Validation Crisis in Psychology","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Qualitative Comparative Analysis Research","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Nomological network; Construct validity; Construct (python library); Cronbach's alpha; Psychology; Structural equation modeling; Point (geometry); Applied psychology; Psychometrics; Computer science; Clinical psychology; Mathematics; Programming language; Machine learning","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005295822,0.00009566797,0.0002185349,0.0001820259,0.0002620595,0.0002014186,0.0007963841,0.000180777,0.001611425],"category_scores_gemma":[0.0008293177,0.00006618059,0.0001057161,0.0004309469,0.0002981355,0.00006396342,0.0003029905,0.0005539714,0.00144328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001541315,"about_ca_system_score_gemma":0.000312642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006396537,"about_ca_topic_score_gemma":0.0168143,"domain_scores_codex":[0.9946223,0.003857879,0.0002843445,0.0003690809,0.0005630791,0.0003032722],"domain_scores_gemma":[0.9978451,0.001229647,0.0001155504,0.0004515317,0.0003138936,0.00004428178],"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":[0.0000530826,0.0001437722,0.0232937,0.00002428033,0.0002046143,0.000002465219,0.05907963,0.000763379,0.00007400249,0.372419,0.5325403,0.01140184],"study_design_scores_gemma":[0.0002075615,0.00002605522,0.01603041,0.00002062029,0.00001358159,3.637496e-8,0.03394516,0.0006319309,0.0001111621,0.373794,0.5749401,0.0002794103],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03544451,0.0008141162,0.01263604,0.07230981,0.0006949132,0.0009315405,0.000005120348,0.00004401782,0.87712],"genre_scores_gemma":[0.9779906,0.001813718,0.0002213247,0.0004172216,0.0001252471,0.00009400531,0.00001495747,0.000007479265,0.0193154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9425461,"threshold_uncertainty_score":0.9993342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.274335715847617,"score_gpt":0.5934682494304809,"score_spread":0.3191325335828639,"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."}}