{"id":"W4411523021","doi":"10.1145/3728919","title":"Assessing Scene Generation Techniques for Testing COLREGS-Compliance of Autonomous Surface Vehicles","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Maritime Navigation and Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Set (abstract data type); Computer science; Logical analysis; Functional requirement; Operations research; Artificial intelligence; Engineering; Software 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":[0.004041529,0.001047318,0.0003309522,0.001402133,0.0002494622,0.0005826653,0.001837782,0.001015857,0.0009421203],"category_scores_gemma":[0.02663684,0.0003469301,0.0006860799,0.0008708245,0.0005971987,0.001196101,0.001035316,0.0005837573,0.0002531559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000643165,"about_ca_system_score_gemma":0.0008082365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002262294,"about_ca_topic_score_gemma":0.0028475,"domain_scores_codex":[0.9950825,0.002449463,0.0003867228,0.0006743217,0.001162397,0.000244581],"domain_scores_gemma":[0.969354,0.02330057,0.002130251,0.002649432,0.002186199,0.0003796029],"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":[0.001398317,0.001709772,0.0448966,0.001104196,0.0003119921,0.0005655491,0.001233376,0.4893942,0.09030801,0.003189606,0.001902462,0.3639859],"study_design_scores_gemma":[0.0001708138,0.001687173,0.009125575,0.0000538517,0.0001044802,0.000406274,0.0003483829,0.9337009,0.05142971,0.001444626,0.001494443,0.00003375106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7581987,0.0003691014,0.2339542,0.0001699779,0.00003011112,0.000618798,0.0004446412,0.003939948,0.002274366],"genre_scores_gemma":[0.7940692,0.0001418712,0.2040523,0.00004700147,0.000007092804,0.0002098353,0.0009780793,0.0002044848,0.0002901583],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004041529,"threshold_uncertainty_score":0.02137387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04127833120726755,"score_gpt":0.2794976332482037,"score_spread":0.2382193020409362,"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."}}