{"id":"W7116384933","doi":"10.1038/s41597-025-06021-5","title":"Responsible AI measures dataset for ethics evaluation of AI systems","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada); McGill University","funders":"","keywords":"Normative; Usability; Set (abstract data type); Interpretation (philosophy); Domain (mathematical analysis); Visualization; Corporate governance","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":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07249495,0.00007543205,0.0001639694,0.0001886019,0.001709639,0.00104869,0.001588738,0.0002251073,0.00003474414],"category_scores_gemma":[0.03862689,0.00007347399,0.00003321246,0.0007988269,0.0009817804,0.001013828,0.0003236177,0.0003349465,0.00001215111],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000973162,"about_ca_system_score_gemma":0.008238133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003323858,"about_ca_topic_score_gemma":0.01306057,"domain_scores_codex":[0.9958704,0.001167169,0.0003084461,0.0004868528,0.001873881,0.0002932853],"domain_scores_gemma":[0.994399,0.001058678,0.0001276058,0.001466355,0.00286325,0.00008515205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001829853,0.00004220771,0.0000545344,0.00006401038,0.00002745459,1.05764e-7,0.003627204,0.00004732024,0.0004515368,0.1988253,0.7948469,0.001995143],"study_design_scores_gemma":[0.0002612403,0.00001199124,0.00008505619,0.0001111151,0.0001110766,4.082565e-8,0.003716335,0.002963635,0.0002406357,0.0705267,0.9218832,0.00008892702],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.01068349,0.007220075,0.02456466,0.3845416,0.05044474,0.009683341,0.450493,0.0002718176,0.0620973],"genre_scores_gemma":[0.944509,0.0001132147,0.0009343124,0.002709925,0.0004096088,0.00006578227,0.03866918,0.00001892425,0.01257008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9338255,"threshold_uncertainty_score":0.9999883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5162686606936119,"score_gpt":0.5809189398766879,"score_spread":0.06465027918307598,"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."}}