{"id":"W4402977984","doi":"10.1145/3640310.3674098","title":"Towards Automated Test Scenario Generation for Assuring COLREGs Compliance of Autonomous Surface Vehicles","year":2024,"lang":"en","type":"article","venue":"","topic":"Maritime Navigation and Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Universitas Brawijaya","keywords":"Compliance (psychology); Test (biology); Computer science; Systems engineering; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002887804,0.001458357,0.0004768615,0.002212747,0.0004243499,0.001700223,0.001591433,0.00144719,0.002012213],"category_scores_gemma":[0.01386545,0.0006197994,0.001770212,0.0006739361,0.001201008,0.001589113,0.001699024,0.001137985,0.0004508319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005915,"about_ca_system_score_gemma":0.002542458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003852158,"about_ca_topic_score_gemma":0.004403239,"domain_scores_codex":[0.9959894,0.001864441,0.0002628147,0.0005227848,0.001079701,0.0002807647],"domain_scores_gemma":[0.9911956,0.005293032,0.0007774949,0.00133748,0.001208217,0.0001882863],"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":[0.0003558323,0.0005796013,0.01168845,0.0006984554,0.0001946846,0.002115198,0.001049544,0.6885343,0.0645111,0.05780863,0.003219327,0.1692449],"study_design_scores_gemma":[0.0000681221,0.0002123628,0.0007169562,0.00009854139,0.00005511753,0.0004021202,0.000205647,0.931635,0.03513603,0.02620818,0.005222712,0.00003926219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06977092,0.0001039109,0.9229313,0.0002878251,0.00003270133,0.0005568232,0.0005693613,0.003682176,0.002065091],"genre_scores_gemma":[0.4130982,0.0001794544,0.5819751,0.0001617381,0.00001679643,0.0004654972,0.0028312,0.0005046462,0.0007673496],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003852158,"threshold_uncertainty_score":0.01527232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03684080707866547,"score_gpt":0.2783086528893733,"score_spread":0.2414678458107078,"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."}}