{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002990898,0.0002835946,0.0002024069,0.0000794044,0.0004810921,0.00007056382,0.0009923936,0.0001757606,0.0002732636],"category_scores_gemma":[0.0005065446,0.0001815054,0.0001182278,0.0005690287,0.0003939547,0.0001396548,0.000354913,0.001166919,0.0001323938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008850158,"about_ca_system_score_gemma":0.00004416231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001365762,"about_ca_topic_score_gemma":0.00002578389,"domain_scores_codex":[0.9978883,0.0001795611,0.000405507,0.0006417567,0.0004856974,0.0003991972],"domain_scores_gemma":[0.998955,0.0003039602,0.0001185502,0.0005009038,0.00005082562,0.00007078114],"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":[0.0001226654,0.0006833242,0.002470328,0.00007122229,0.00007184094,0.00005381532,0.002095913,0.003031412,0.08251484,0.818477,0.03482206,0.05558558],"study_design_scores_gemma":[0.0003230685,0.0001624716,0.001863858,0.0001452092,0.00003440516,0.00005234768,0.0002822022,0.008631137,0.7656737,0.1545511,0.06783717,0.0004433545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3122717,0.02720925,0.09048296,0.316063,0.01452748,0.003186426,0.0001647593,0.0009992968,0.2350952],"genre_scores_gemma":[0.9556034,0.0001539074,0.001732518,0.04069384,0.0001208109,0.00005971606,0.000009021076,0.00001326681,0.001613483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6831589,"threshold_uncertainty_score":0.7401575,"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."}}