{"id":"W3185425515","doi":"10.1007/s10515-022-00337-x","title":"How to certify machine learning based safety-critical systems? A systematic literature review","year":2022,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; Polytechnique Montréal","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Certification; Computer science; Life-critical system; Context (archaeology); Domain (mathematical analysis); Systematic review; Robustness (evolution); Engineering management; Artificial intelligence; Software; Engineering; Management; Political science","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001406825,0.0004281841,0.0007825517,0.000425827,0.0005728494,0.0006086872,0.001387137,0.00009228921,0.00001945783],"category_scores_gemma":[0.008467774,0.000429455,0.0001646022,0.002211694,0.00001201885,0.0005370849,0.0008418651,0.001248858,0.00002296507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003916226,"about_ca_system_score_gemma":0.00007656649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008362292,"about_ca_topic_score_gemma":2.61679e-7,"domain_scores_codex":[0.99645,0.0006909595,0.0006012429,0.0007049338,0.000886421,0.0006664433],"domain_scores_gemma":[0.9972241,0.001282813,0.0001658678,0.0008988986,0.0001617654,0.0002665541],"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":[0.000004301051,0.00002034495,0.00005453999,0.04866236,0.00003850646,0.0003474508,0.000286965,0.9479229,0.00005339851,0.002226597,0.0002752152,0.0001073871],"study_design_scores_gemma":[0.0002054682,0.00009064701,0.00002846682,0.02850188,0.00004670135,0.000288215,0.00002150302,0.9647456,0.000009697708,0.000002250672,0.005588697,0.000470849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005866202,0.03629098,0.9515015,0.00216929,0.001131377,0.0009413788,0.00001780517,0.007877502,0.00001143296],"genre_scores_gemma":[0.7475262,0.0002735623,0.2480417,0.001691554,0.000190714,0.001319912,0.0001500822,0.0002560306,0.0005501799],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7474676,"threshold_uncertainty_score":0.9998843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007356704105584707,"score_gpt":0.2339043536913897,"score_spread":0.226547649585805,"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."}}