{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005923716,0.002488074,0.001379859,0.003242035,0.0008038545,0.002825805,0.005625123,0.002167857,0.00594512],"category_scores_gemma":[0.01344693,0.001325637,0.003004641,0.001515941,0.002973966,0.002773588,0.003338803,0.003704058,0.001672292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001612604,"about_ca_system_score_gemma":0.002870499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00630772,"about_ca_topic_score_gemma":0.007736673,"domain_scores_codex":[0.9959014,0.001622124,0.0003469729,0.0004573818,0.001379796,0.0002922442],"domain_scores_gemma":[0.995127,0.003291266,0.0003151619,0.0005755335,0.0005194432,0.0001714948],"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":[0.0001877743,0.0002663126,0.002213149,0.001110172,0.0002299811,0.0006426605,0.0003911043,0.5233328,0.005850151,0.2609517,0.01121904,0.193605],"study_design_scores_gemma":[0.00007222302,0.00008445418,0.0002050571,0.0002150913,0.00004447308,0.000294065,0.00003557273,0.8724615,0.00335928,0.1014926,0.02169538,0.00004032495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007452509,0.0001935575,0.9927011,0.0001081297,0.000019077,0.0001798499,0.0001336174,0.004496886,0.001422591],"genre_scores_gemma":[0.03928959,0.0004781577,0.9561993,0.0001540897,0.00003493715,0.0007901794,0.0008346487,0.0009442907,0.00127476],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00630772,"threshold_uncertainty_score":0.03132796,"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."}}