{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001789041,0.0001120915,0.0002028066,0.0002232175,0.001352811,0.0001197302,0.0009803874,0.00009525093,0.00001774572],"category_scores_gemma":[0.001291083,0.00008520736,0.00009769938,0.001422048,0.001608756,0.0005170817,0.0003154832,0.0001549549,0.00000501678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002385898,"about_ca_system_score_gemma":0.0001718759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002931383,"about_ca_topic_score_gemma":0.00002283634,"domain_scores_codex":[0.9981666,0.00001688833,0.0004102457,0.0003370389,0.0008147374,0.0002545134],"domain_scores_gemma":[0.998899,0.0002259071,0.0003707605,0.000009614336,0.0004449509,0.00004970533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001510684,0.0005797577,0.09184577,0.0000423323,0.00007921421,1.158532e-8,0.01669377,0.0001761247,0.1730219,0.6963584,0.009124299,0.01192729],"study_design_scores_gemma":[0.0002290555,0.0002338795,0.08992946,0.00017231,0.00004174817,2.665743e-7,0.01357162,0.0002134255,0.5686252,0.3235469,0.003182984,0.0002531917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415196,0.00009194675,0.000001159299,0.004442874,0.00007056132,0.0008017253,0.00002467996,0.00003279847,0.05301462],"genre_scores_gemma":[0.9961073,0.00004282398,0.002426853,0.0001755057,0.00007520103,0.0001018243,8.542509e-8,0.000003435942,0.001067015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3956032,"threshold_uncertainty_score":0.9999473,"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."}}