{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003737702,0.000121254,0.0002179466,0.00003949513,0.0003537135,0.00004300657,0.000496611,0.00003619499,0.00008054651],"category_scores_gemma":[0.000425852,0.00005398609,0.0003794027,0.0001475986,0.0001652657,0.00006389077,0.000121022,0.0003771557,4.913142e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000279015,"about_ca_system_score_gemma":0.0003399843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006656297,"about_ca_topic_score_gemma":0.0001671155,"domain_scores_codex":[0.9982678,0.0002801728,0.0005463836,0.0001210402,0.0005776002,0.0002070178],"domain_scores_gemma":[0.9962729,0.001645412,0.0007836052,0.0002598237,0.001010964,0.00002730632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001184037,0.001542217,0.0406197,0.0006228302,0.00612662,0.00001039729,0.04759641,0.0004329821,0.006635959,0.06826882,0.01140015,0.8155599],"study_design_scores_gemma":[0.004939717,0.001018279,0.8220695,0.0007731736,0.00133001,0.00007636112,0.1086718,0.01046801,0.002943357,0.02853986,0.01884,0.0003299731],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7578746,0.002154776,0.1776517,0.03524958,0.00802929,0.002283179,0.0001116427,0.00001392652,0.01663132],"genre_scores_gemma":[0.9980682,0.000007531468,0.0003235987,0.0009121959,0.0003548735,0.00004451393,2.951258e-7,0.000006697651,0.0002821196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8152299,"threshold_uncertainty_score":0.2720514,"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."}}