{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000435471,0.0004230267,0.0007464204,0.0001328689,0.00005832925,0.00004736839,0.0008740754,0.0005740158,0.000009272087],"category_scores_gemma":[0.0003304689,0.0003642176,0.0002904608,0.0002418023,0.00003980516,0.00004871,0.0002155995,0.001016709,0.00002316644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001900195,"about_ca_system_score_gemma":0.0001477147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009701273,"about_ca_topic_score_gemma":0.000004421302,"domain_scores_codex":[0.9982651,0.00003633931,0.0007332677,0.0003736073,0.0001961117,0.0003955742],"domain_scores_gemma":[0.9968575,0.001373114,0.0001582034,0.001397884,0.0001605289,0.00005274866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009613589,0.00001041489,0.00821845,0.006632834,0.0006301783,0.000001457247,0.000204514,0.9763113,0.0001521787,0.005453564,0.002231858,0.0001436204],"study_design_scores_gemma":[0.0007690251,0.00004703837,0.03812103,0.01148125,0.000477489,0.000008968395,0.0002020601,0.7904004,0.003408376,0.001495048,0.152169,0.00142023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0239376,0.01238094,0.9439112,0.0003292962,0.01417027,0.002424903,0.0002416972,0.0009580638,0.001646009],"genre_scores_gemma":[0.993454,0.0001788778,0.003278986,0.00003828103,0.0006484778,0.001451268,0.00001853153,0.0000963663,0.000835193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9695164,"threshold_uncertainty_score":0.999881,"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."}}