{"id":"W4382930431","doi":"10.1016/j.scico.2023.102990","title":"AmbieGen: A search-based framework for autonomous systems testing","year":2023,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Modular design; Software deployment; Autonomous system (mathematics); Architecture; Robot; Scenario testing; Test case; Distributed computing; Artificial intelligence; Software engineering; Machine learning; Programming language","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":[0.003026661,0.0001830308,0.0002663914,0.0006289408,0.0004936773,0.0007383706,0.00220505,0.00007015801,2.115656e-7],"category_scores_gemma":[0.0009302573,0.0001737018,0.00008875638,0.004521846,0.0004578647,0.0004331525,0.0005610158,0.0001625104,0.000009489309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007391203,"about_ca_system_score_gemma":0.0005844146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006778606,"about_ca_topic_score_gemma":2.364464e-7,"domain_scores_codex":[0.9973008,0.00004965808,0.0003890664,0.000708943,0.00071013,0.0008413907],"domain_scores_gemma":[0.9967106,0.001507985,0.0001909885,0.0008218538,0.0005950604,0.0001735162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003992316,0.00008535866,0.002481347,0.0002824841,0.000008709315,0.00001589158,0.0007197911,0.01719073,0.0005578463,0.05793732,0.0006403649,0.9200762],"study_design_scores_gemma":[0.000117661,0.0003794812,0.0008630721,0.0003784269,0.000003130017,0.00001245612,0.00000915123,0.9767142,0.001579773,0.0194353,0.000292425,0.0002149163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01139372,0.00003744784,0.9749328,0.0002538564,0.0007572395,0.0006193952,0.000001661613,0.01197753,0.00002635492],"genre_scores_gemma":[0.3949763,1.703143e-7,0.6048055,0.0000382906,0.00008575556,0.00007676825,9.884722e-7,0.0000108619,0.00000530928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9595235,"threshold_uncertainty_score":0.7120125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0676608071989877,"score_gpt":0.3268068828846064,"score_spread":0.2591460756856187,"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."}}