{"id":"W4407081039","doi":"10.1017/bpp.2024.50","title":"Catch me if you can: Using machine learning and behavioral interventions to reduce unethical behavior","year":2025,"lang":"en","type":"article","venue":"Behavioural Public Policy","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Earnings; Psychological intervention; Agency (philosophy); Intervention (counseling); Blueprint; Perspective (graphical); Behavioral economics; Unemployment; Business; Computer science; Psychology; Economics; Artificial intelligence; Microeconomics; Accounting; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006604394,0.0003342801,0.0004428093,0.0006755709,0.001727591,0.0005142037,0.0004862805,0.000271188,0.0001746708],"category_scores_gemma":[0.0002950305,0.0003766052,0.0002415249,0.0008179217,0.0007040074,0.0004257675,0.0007251885,0.0006188721,0.00001739011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001387334,"about_ca_system_score_gemma":0.0007174446,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3203271,"about_ca_topic_score_gemma":0.04321933,"domain_scores_codex":[0.9971857,0.0003120874,0.000610383,0.0006169658,0.0003226457,0.0009521864],"domain_scores_gemma":[0.9987673,0.00005195387,0.0001600081,0.0002711363,0.0001847606,0.000564828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002032697,0.0006568653,0.9351118,0.00001947361,0.00002837215,0.00001899365,0.0100998,0.000001928087,0.006836478,0.03566167,0.0004212528,0.01112307],"study_design_scores_gemma":[0.00728334,0.001830275,0.8058915,0.001067226,0.002663106,0.0001522577,0.08467819,0.0002106107,0.01249737,0.004513232,0.07296844,0.006244456],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9732438,0.0004389653,0.00002223714,0.02280427,0.000479023,0.0007711615,0.0001117284,0.000220989,0.001907865],"genre_scores_gemma":[0.9900744,0.00005135601,0.001266888,0.000407339,0.0001655284,0.0002229499,0.00004446331,0.00003720825,0.007729883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2771078,"threshold_uncertainty_score":0.9998686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1395465510056076,"score_gpt":0.4546537608710862,"score_spread":0.3151072098654785,"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."}}