{"id":"W3003092138","doi":"10.4271/2020-01-0738","title":"Bridging the Gap between ISO 26262 and Machine Learning: A Survey of Techniques for Developing Confidence in Machine Learning Systems","year":2020,"lang":"en","type":"article","venue":"SAE International Journal of Advances and Current Practices in Mobility","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Critical Systems Labs","funders":"","keywords":"Bridging (networking); Computer science; Functional safety; Class (philosophy); Engineering; Artificial intelligence; Systems engineering; Reliability engineering; Computer security","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":[],"consensus_categories":[],"category_scores_codex":[0.004652167,0.0001475746,0.0003622753,0.0001410689,0.00008989156,0.0001736084,0.0007720084,0.00004001999,0.00000141631],"category_scores_gemma":[0.008202869,0.0001141604,0.00004316797,0.0002648668,0.0001086969,0.001692481,0.0003689658,0.0009440964,9.260283e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007031381,"about_ca_system_score_gemma":0.0001132737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005288227,"about_ca_topic_score_gemma":0.0002232202,"domain_scores_codex":[0.9975141,0.0007704488,0.0008216012,0.0002989853,0.0004359087,0.0001589978],"domain_scores_gemma":[0.9947142,0.002607752,0.002085797,0.00009602616,0.0004441895,0.00005204541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001984819,0.00004257519,0.8283034,0.0002144434,0.0000390074,0.000006766781,0.001149663,0.01709263,0.00009000357,0.001307823,0.000001761252,0.1515534],"study_design_scores_gemma":[0.001594943,0.0005681735,0.3141207,0.001155285,0.0000329773,0.00009222236,0.0006019608,0.6659321,0.0002974065,0.002163443,0.01307533,0.0003655258],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.213185,0.01748669,0.7656617,0.002787441,0.0005025273,0.0003231167,0.00001324305,0.00001995487,0.0000202792],"genre_scores_gemma":[0.9870192,0.003861314,0.008929187,0.00002997077,0.0001380815,0.000007798683,0.000005483027,0.00000711105,0.000001849374],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7738342,"threshold_uncertainty_score":0.9820193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1035672139051613,"score_gpt":0.393370896460878,"score_spread":0.2898036825557167,"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."}}