{"id":"W4286488146","doi":"10.1145/3550270","title":"Parameter Coverage for Testing of Autonomous Driving Systems under Uncertainty","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; JST-Mirai Program; European Regional Development Fund; Japan Science and Technology Agency; University of Waterloo; Exploratory Research for Advanced Technology; Science Foundation Ireland","keywords":"Computer science; Correctness; Heuristics; Trustworthiness; Process (computing); Cover (algebra); Operations research; Reliability engineering; Mathematical optimization; Risk analysis (engineering); Algorithm; Computer security","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001610365,0.0001307877,0.000329773,0.0002630632,0.0002654385,0.00003567729,0.0004737508,0.00006436862,0.000008000967],"category_scores_gemma":[0.002913735,0.0001338833,0.0001142335,0.0004825775,0.00003656271,0.00008834586,0.00005402951,0.000313057,4.220248e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008654202,"about_ca_system_score_gemma":0.00007531814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001054934,"about_ca_topic_score_gemma":0.00000165769,"domain_scores_codex":[0.9985334,0.000343696,0.0002794736,0.00037565,0.0001840064,0.0002837263],"domain_scores_gemma":[0.9833388,0.01590977,0.00006571726,0.0005229283,0.00008742582,0.00007530549],"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":[0.000009086564,0.0000411814,0.0002271737,0.00007705827,0.00007115202,0.000001544867,0.0001670081,0.9334105,0.0004662123,0.0007441667,0.000003900679,0.06478102],"study_design_scores_gemma":[0.0006212847,0.0006940136,0.0009816682,0.00004028096,0.00006475855,0.000101261,0.0001652301,0.9895133,0.001035126,0.003568826,0.00287103,0.0003431954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04785325,0.0001756127,0.9510717,0.0001056923,0.0003672341,0.0001892382,0.00001991388,0.0002161688,0.000001218919],"genre_scores_gemma":[0.4478139,0.00001136864,0.5519018,0.00003193781,0.00001254547,0.0001633597,0.000002100307,0.00001098144,0.00005199765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3999607,"threshold_uncertainty_score":0.5459601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1073477262309126,"score_gpt":0.3267423154097948,"score_spread":0.2193945891788822,"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."}}