{"id":"W6963144375","doi":"10.17605/osf.io/tg4kv","title":"Can ChatGPT Outperform Humans in Faking a Personality Assessment While Avoiding Detection?","year":2024,"lang":"en","type":"other","venue":"Open Science Framework","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council","keywords":"Personality; Personality Assessment Inventory; Big Five personality traits; Affect (linguistics); Interview","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01161953,0.001060042,0.0009574135,0.001098961,0.0009229291,0.00314231,0.001025495,0.001731657,0.0136021],"category_scores_gemma":[0.05962777,0.0002030867,0.0004186328,0.000481968,0.001016105,0.004059447,0.001484618,0.001362823,0.005359952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006248501,"about_ca_system_score_gemma":0.0007879325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001483637,"about_ca_topic_score_gemma":0.002542016,"domain_scores_codex":[0.995103,0.002525606,0.0002287417,0.0006456964,0.001132384,0.0003645813],"domain_scores_gemma":[0.9413335,0.03473917,0.00643535,0.008598233,0.004505631,0.004388107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007267207,0.003973322,0.1971475,0.002019995,0.0004783963,0.0007130321,0.005065467,0.005963483,0.01566029,0.01132829,0.06097534,0.6894076],"study_design_scores_gemma":[0.001788183,0.01990671,0.4987393,0.001328362,0.001014895,0.00545343,0.01211218,0.197604,0.03394644,0.09398277,0.1330138,0.001110059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.862197,0.001914055,0.03976599,0.005003163,0.001127387,0.0007513727,0.001444778,0.005005383,0.08279086],"genre_scores_gemma":[0.9693802,0.0003190391,0.01849594,0.001004444,0.0001317648,0.0001756015,0.0005128348,0.0001598823,0.009820352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0136021,"threshold_uncertainty_score":0.06145066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05269900250611558,"score_gpt":0.3930098290303357,"score_spread":0.3403108265242201,"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."}}