{"id":"W4413048258","doi":"10.1080/00223891.2025.2531187","title":"Improving the Measurement of the Big Five via Alternative Formats for the BFI-2","year":2025,"lang":"en","type":"article","venue":"Journal of Personality Assessment","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Validation test; Psychometrics; Test validity; Social psychology; Developmental psychology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0275336,0.001016896,0.0007143561,0.002520339,0.00101683,0.001951592,0.001729515,0.000691588,0.006333343],"category_scores_gemma":[0.07250993,0.0004833839,0.001978395,0.0030617,0.0006898019,0.001750969,0.002121592,0.002206372,0.0009452582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002505192,"about_ca_system_score_gemma":0.003672577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01370101,"about_ca_topic_score_gemma":0.03023833,"domain_scores_codex":[0.9812951,0.009630468,0.002650764,0.0009678403,0.004838944,0.0006168612],"domain_scores_gemma":[0.9659313,0.0152571,0.00285417,0.002988511,0.01218198,0.0007869961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001097204,0.001145006,0.1884678,0.001853451,0.000590856,0.0002288265,0.009018217,0.002277162,0.005483551,0.01368513,0.03018489,0.7459679],"study_design_scores_gemma":[0.0007618421,0.002195246,0.8699226,0.002063596,0.0005791344,0.0005064333,0.005843628,0.01278498,0.007723615,0.02463592,0.0724008,0.0005821976],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6550134,0.002869455,0.2686458,0.003869199,0.002446437,0.01732424,0.01238599,0.0009020978,0.03654351],"genre_scores_gemma":[0.5022807,0.001945907,0.4469362,0.001419998,0.0002625544,0.03102315,0.009216328,0.000198304,0.00671689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0275336,"threshold_uncertainty_score":0.1456134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08514145048496488,"score_gpt":0.3774184727130762,"score_spread":0.2922770222281112,"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."}}