{"id":"W4411336324","doi":"10.1073/pnas.2319942121","title":"Humans program artificial delegates to accurately solve collective-risk dilemmas but lack precision","year":2025,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Horizon 2020 Framework Programme; Service Public de Wallonie; Fonds Wetenschappelijk Onderzoek; Vlaamse regering; European Commission; Vlaamse Overheid; Fundação para a Ciência e a Tecnologia; Fonds De La Recherche Scientifique - FNRS","keywords":"Delegate; Delegation; Public good; Computer science; Computer security; Dilemma; Test (biology); Order (exchange); Action (physics); Artificial intelligence; Public relations; Microeconomics; Economics; Political science","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":[0.003955905,0.0007024723,0.000430562,0.0002875543,0.0005991154,0.001847317,0.0009293185,0.001169216,0.005227024],"category_scores_gemma":[0.02518106,0.0003956925,0.0003372692,0.0002002803,0.002788332,0.002463914,0.002442345,0.001596093,0.001113199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005581835,"about_ca_system_score_gemma":0.0006922801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005812966,"about_ca_topic_score_gemma":0.0004170541,"domain_scores_codex":[0.9964308,0.001988354,0.0001588792,0.0005800173,0.0005685713,0.000273317],"domain_scores_gemma":[0.9844862,0.007444935,0.002571227,0.00416769,0.0005267943,0.0008031537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002745739,0.002591999,0.08017798,0.001314966,0.000710501,0.0006609366,0.01412649,0.1826382,0.2453288,0.218799,0.006750273,0.2441552],"study_design_scores_gemma":[0.001099359,0.004174185,0.05603428,0.000286693,0.0002265926,0.00102015,0.00550712,0.4222528,0.08910931,0.3650195,0.05492957,0.0003405235],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8764563,0.0001506206,0.1013771,0.001212178,0.00006934092,0.0001188751,0.00003809961,0.000379787,0.02019772],"genre_scores_gemma":[0.9788437,0.00004899426,0.01808614,0.0002518429,0.00001342681,0.0001096357,0.00003148242,0.000052252,0.002562458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005227024,"threshold_uncertainty_score":0.02092105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1468897726697906,"score_gpt":0.4337349156709368,"score_spread":0.2868451430011462,"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."}}