{"id":"W4406334158","doi":"10.1038/s42256-024-00969-6","title":"Investigating machine moral judgement through the Delphi experiment","year":2025,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Psychology of Moral and Emotional Judgment","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Naval Information Warfare Center Pacific; Defense Advanced Research Projects Agency; Allen Institute for Artificial Intelligence","keywords":"Morality; Judgement; Delphi; Delphi method; Computer science; Artificial intelligence; Engineering ethics; Psychology; Epistemology; Engineering; Philosophy","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":[0.02939984,0.0009502898,0.0007529735,0.0007863606,0.002676738,0.0027684,0.001750388,0.002705416,0.01064351],"category_scores_gemma":[0.1111489,0.0004470605,0.000749159,0.0007677093,0.004178002,0.004997962,0.005108867,0.005827143,0.002447354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001482127,"about_ca_system_score_gemma":0.001740099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001429668,"about_ca_topic_score_gemma":0.001931158,"domain_scores_codex":[0.9767373,0.01876486,0.0005524665,0.001736803,0.001536417,0.0006721129],"domain_scores_gemma":[0.8467667,0.1308602,0.0050912,0.009539571,0.005502228,0.002239952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.009844409,0.01058589,0.09585464,0.002668227,0.000707346,0.001994676,0.09603766,0.1021842,0.01895852,0.324803,0.08495912,0.2514024],"study_design_scores_gemma":[0.001695896,0.004626832,0.03881559,0.0008040842,0.0001869915,0.0006631929,0.02294951,0.4290084,0.02251645,0.3655538,0.1125103,0.0006690128],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8524456,0.000303851,0.08141395,0.005534979,0.0006744849,0.001706692,0.001120991,0.0006747551,0.05612469],"genre_scores_gemma":[0.9395304,0.0001166551,0.04903783,0.002493012,0.0001345977,0.002639199,0.000764917,0.0001835286,0.005099938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02939984,"threshold_uncertainty_score":0.1554831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0786320923324565,"score_gpt":0.3533610626654572,"score_spread":0.2747289703330007,"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."}}