{"id":"W4408605051","doi":"10.1007/s43681-025-00703-x","title":"Metaethical perspectives on ‘benchmarking’ AI ethics","year":2025,"lang":"en","type":"article","venue":"AI and Ethics","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Schwartz/Reisman Emergency Medicine Institute; University of Toronto","funders":"Dalhousie University","keywords":"Benchmarking; Cornerstone; Variety (cybernetics); Set (abstract data type); Value (mathematics); Benchmark (surveying); Epistemology; Engineering ethics; Computer science; Artificial intelligence; Sociology; Philosophy; Management; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","sts","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.008554829,0.0001582457,0.0002402821,0.000115537,0.002861554,0.0004795196,0.0002582571,0.00180809,0.00008972178],"category_scores_gemma":[0.01671301,0.0001487047,0.000107156,0.0003969878,0.001779131,0.0002666938,0.00009148297,0.007695891,0.00001708325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001023951,"about_ca_system_score_gemma":0.001815592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00326983,"about_ca_topic_score_gemma":0.004482617,"domain_scores_codex":[0.9970033,0.001183766,0.0002021672,0.000365408,0.0008296502,0.0004156796],"domain_scores_gemma":[0.9933832,0.005292924,0.00005556343,0.0002060099,0.0008672936,0.0001949848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001323046,0.00004329961,0.0001623941,0.00002533422,0.00003588087,0.000002955133,0.2206147,0.000003067462,0.00001027214,0.7743732,0.003236484,0.001479164],"study_design_scores_gemma":[0.0002805484,0.0001479643,0.001333926,0.0001908151,0.00006072761,3.556619e-7,0.05644149,0.00006972253,0.00003949845,0.6504573,0.2906898,0.0002879313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.006618015,0.0008672474,0.001039309,0.8001258,0.0008811085,0.000159963,0.000006223251,0.0001084527,0.1901939],"genre_scores_gemma":[0.8895057,0.00613492,0.0001825299,0.1010233,0.0004382407,0.000005408618,0.000002049439,0.00001041958,0.002697449],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.8828877,"threshold_uncertainty_score":0.9994878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08713312055306624,"score_gpt":0.4764134192578392,"score_spread":0.389280298704773,"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."}}