{"id":"W4396878382","doi":"10.2139/ssrn.4826678","title":"Hacking the Perfect Score on High-Stakes Personality Assessments with Generative Ai","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Personality Traits and Psychology","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Generative grammar; Hacker; Psychology; Personality; Computer science; Social psychology; Artificial intelligence; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007444134,0.00064191,0.0005365515,0.001433116,0.0004397155,0.00192598,0.0005414914,0.0009631769,0.005051009],"category_scores_gemma":[0.06561954,0.0002678426,0.0004746777,0.0007325382,0.0009136517,0.001824016,0.002240182,0.001414609,0.002294185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003514212,"about_ca_system_score_gemma":0.0004517994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007828093,"about_ca_topic_score_gemma":0.001435244,"domain_scores_codex":[0.9945873,0.002282706,0.0004046276,0.0007874516,0.001477616,0.0004602382],"domain_scores_gemma":[0.9639696,0.02014371,0.003329469,0.007942095,0.003204986,0.001410106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001847328,0.0007961497,0.5768237,0.000130805,0.0002665092,0.0002468604,0.002672756,0.004546435,0.005625803,0.009970411,0.01275274,0.3843206],"study_design_scores_gemma":[0.0001313035,0.00214874,0.8279901,0.0002055139,0.0001833584,0.001019637,0.002019496,0.07919142,0.01847995,0.0566576,0.01179047,0.000182302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9416276,0.0001294028,0.02748281,0.0006537392,0.0003662703,0.0001543502,0.0005540107,0.00147331,0.02755846],"genre_scores_gemma":[0.9903699,0.00003554735,0.007059237,0.00009447011,0.00002604117,0.00006436129,0.0002186887,0.00006529708,0.002066453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007444134,"threshold_uncertainty_score":0.03936881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04840659160015236,"score_gpt":0.3740427270741273,"score_spread":0.3256361354739749,"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."}}