{"id":"W4415306711","doi":"10.48550/arxiv.2504.16937","title":"A Framework for the Assurance of AI-Enabled Systems","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Software deployment; Stakeholder; Process (computing); Constructive; Set (abstract data type); Flexibility (engineering); Risk management","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":[0.03730614,0.001565582,0.0009450075,0.005614861,0.004837966,0.01336629,0.004386439,0.009180486,0.004544817],"category_scores_gemma":[0.0450407,0.0009802753,0.002466378,0.002625854,0.02646622,0.02057778,0.008435,0.008746058,0.001156214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008048751,"about_ca_system_score_gemma":0.00828577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008582978,"about_ca_topic_score_gemma":0.003173152,"domain_scores_codex":[0.9667192,0.0178916,0.003213187,0.002741829,0.007798772,0.001635446],"domain_scores_gemma":[0.9524589,0.02836009,0.003119026,0.00669672,0.007890488,0.001474815],"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":[0.000003712605,0.000008299872,0.00007747957,0.00002866927,0.000004060518,0.00005001808,0.0004098446,0.002064087,0.00006934422,0.9945009,0.0004729519,0.002310728],"study_design_scores_gemma":[0.00001222569,0.00002744471,0.00007955139,0.0001394301,0.000009871882,0.00008174612,0.0003725378,0.0150042,0.0003242332,0.9589347,0.02499208,0.00002210133],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004619938,0.001355533,0.9303919,0.01814137,0.0002804047,0.0003333695,0.0001474438,0.0004204065,0.04430971],"genre_scores_gemma":[0.4479019,0.002288563,0.5333553,0.002025958,0.0007033474,0.001226196,0.0003063504,0.0002103012,0.01198198],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03730614,"threshold_uncertainty_score":0.1972961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02738319154217082,"score_gpt":0.2604022312992607,"score_spread":0.2330190397570899,"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."}}