{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002515129,0.0001599248,0.0002320326,0.00007178172,0.000103999,0.00008172318,0.0005153813,0.00009500582,0.000001521296],"category_scores_gemma":[0.00228011,0.0001487821,0.00007591161,0.0004130173,0.00003583888,0.0001797302,0.000107228,0.0001476797,3.709396e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008784474,"about_ca_system_score_gemma":0.00002707487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007337958,"about_ca_topic_score_gemma":3.301049e-7,"domain_scores_codex":[0.9991871,0.000001981744,0.0003405957,0.0001585312,0.0001401426,0.0001716085],"domain_scores_gemma":[0.9990988,0.0002204614,0.0001006574,0.0002260929,0.0003285738,0.00002538471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001968911,0.00006646834,0.01179239,0.003559083,0.00009601139,1.473968e-7,0.0001062298,0.09983768,0.8307676,0.002928355,0.005513684,0.04531266],"study_design_scores_gemma":[0.0001850508,0.00002743407,0.004206126,0.000815869,0.00002175782,0.000001217293,0.00001649473,0.2304831,0.7626671,0.0002414796,0.001178279,0.0001561706],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9302683,0.0003541961,0.06469292,0.0003803038,0.0005548616,0.0009954894,0.00003423081,0.001489101,0.001230558],"genre_scores_gemma":[0.7124808,0.000005181173,0.2872811,0.00002928608,0.0000473717,0.00003393269,0.000002862074,0.00002848033,0.00009100765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2225882,"threshold_uncertainty_score":0.6067159,"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."}}