{"id":"W4408964547","doi":"10.1177/10731911251328604","title":"Reading the Mind in the Eyes Test Scores Demonstrate Poor Structural Properties in Nine Large Non-Clinical Samples","year":2025,"lang":"en","type":"article","venue":"Assessment","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Macquarie University; Australian Government; Australian Research Council; John Templeton Foundation","keywords":"Reliability (semiconductor); Psychology; Confirmatory factor analysis; Exploratory factor analysis; Internal consistency; Test (biology); Reading (process); Consistency (knowledge bases); Structural equation modeling; Psychometrics; Cognitive psychology; Clinical psychology; Statistics; Artificial intelligence; Computer science; Mathematics; Ecology","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":[],"consensus_categories":[],"category_scores_codex":[0.001103544,0.0001178309,0.0001881024,0.00008884175,0.0001653808,0.00005622149,0.0003208321,0.00008334798,0.0003801299],"category_scores_gemma":[0.00007036355,0.00006154998,0.00008210314,0.0002551724,0.0001231045,0.0000693907,0.00006038422,0.0004823024,0.00002175769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005118029,"about_ca_system_score_gemma":0.0001218202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00157739,"about_ca_topic_score_gemma":0.004809272,"domain_scores_codex":[0.9983485,0.0003699632,0.0005799762,0.0002353415,0.0001148245,0.0003513668],"domain_scores_gemma":[0.9991587,0.0004017054,0.00008801131,0.0002910081,0.00002938174,0.00003123876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002695786,0.0003907002,0.9707549,0.00001290519,0.0000123099,0.00001097427,0.000573292,0.000001060833,0.00005877217,0.003033272,0.002602105,0.02252281],"study_design_scores_gemma":[0.0006381727,0.0001888187,0.9930372,0.0001732431,0.00001848127,0.000003617768,0.003920462,0.0001879479,0.00002985718,0.0002363189,0.001497673,0.00006821164],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884296,0.0002363404,0.00003307466,0.005553889,0.0005813846,0.0005626929,0.00002697502,0.000009061284,0.00456697],"genre_scores_gemma":[0.9974369,0.0000152847,0.0002306092,0.0008573017,0.00006179063,0.0001998297,0.0000140648,0.000006260163,0.001178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0224546,"threshold_uncertainty_score":0.4162156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.118385895957399,"score_gpt":0.496865283711472,"score_spread":0.378479387754073,"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."}}