{"id":"W4388469715","doi":"10.1109/tse.2023.3327575","title":"Identifying the Hazard Boundary of ML-Enabled Autonomous Systems Using Cooperative Coevolutionary Search","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Computer science; Boundary (topology); Hazard; Context (archaeology); Component (thermodynamics); Genetic algorithm; Artificial intelligence; Metaheuristic; Machine learning; Algorithm; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0009325526,0.00019734,0.0002957646,0.0005469967,0.0005909922,0.0002575455,0.0007470491,0.00009842812,0.00001618802],"category_scores_gemma":[0.00008408856,0.0001680396,0.0001976475,0.002567114,0.0001060101,0.0004924188,0.00002098304,0.0005173591,0.00006343061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002540048,"about_ca_system_score_gemma":0.0003188515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001565075,"about_ca_topic_score_gemma":0.000004960262,"domain_scores_codex":[0.9978389,0.0001558046,0.000406298,0.0004199363,0.0007059787,0.0004730837],"domain_scores_gemma":[0.9979694,0.0009261783,0.00005000125,0.0006625195,0.0002832013,0.0001086789],"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":[0.000005692197,0.00004255931,0.00008249682,0.0001259538,0.0001264951,0.00001583238,0.0006026134,0.9953357,0.001687659,0.0002207778,0.00004597628,0.001708262],"study_design_scores_gemma":[0.0001775983,0.00004783653,0.0005049598,0.0001400112,0.00002221554,0.00002594623,0.0001820488,0.9933731,0.005101407,0.00002110615,0.0002198311,0.0001839553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07473881,0.0002963547,0.9231799,0.00006190126,0.0007115393,0.0002751079,0.00002404833,0.0007071718,0.000005209347],"genre_scores_gemma":[0.9876773,0.00008149367,0.01183271,0.0000111573,0.00004830679,0.00006368299,0.000003261601,0.00002867629,0.0002533965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9129385,"threshold_uncertainty_score":0.6852458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03903614166885182,"score_gpt":0.2854306910932624,"score_spread":0.2463945494244106,"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."}}