{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007910023,0.0006733678,0.0008046697,0.001687585,0.0008333661,0.003610855,0.005042766,0.0006146729,0.006792918],"category_scores_gemma":[0.0006915905,0.0006450863,0.0001489931,0.005581331,0.0009890281,0.0007170457,0.002480878,0.003460221,0.004661002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003324339,"about_ca_system_score_gemma":0.001580089,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01058935,"about_ca_topic_score_gemma":0.02960307,"domain_scores_codex":[0.9934047,0.0002383778,0.0005654862,0.002372473,0.002063771,0.001355174],"domain_scores_gemma":[0.9971806,0.0001272076,0.0004725593,0.001783371,0.0001025486,0.0003337253],"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":[0.0002025211,0.002724479,0.08707932,0.003195919,0.0009994467,0.001228477,0.1162158,0.0005052124,0.02789851,0.2320268,0.4750568,0.05286672],"study_design_scores_gemma":[0.0007268941,0.0002550656,0.009839638,0.01947158,0.0001826028,0.00004679388,0.00862163,0.003057367,0.0009947268,0.02273734,0.9303179,0.00374843],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.003479962,0.0003247086,0.001008613,0.0005538281,0.002892135,0.002130181,0.0002375154,0.0003823164,0.9889907],"genre_scores_gemma":[0.7701199,0.00001795336,0.00719945,0.0003050176,0.000640508,0.0004296079,0.00001105266,0.001071822,0.2202047],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7687861,"threshold_uncertainty_score":0.9996001,"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."}}