{"id":"W4415115558","doi":"10.1007/s13437-025-00389-2","title":"Risk maturity model for maritime authorities: testing the internal consistency and inter-rater reliability of the R-Mare matrix","year":2025,"lang":"en","type":"article","venue":"WMU Journal of Maritime Affairs","topic":"Maritime Navigation and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Interreg; Natural Sciences and Engineering Research Council of Canada; Aalto-Yliopisto","keywords":"Reliability (semiconductor); Intraclass correlation; Consistency (knowledge bases); Risk management; Test (biology); Risk assessment; Usability; Maturity (psychological)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001529146,0.0002126024,0.0004146419,0.0001034415,0.0002102343,0.00008949979,0.0004758298,0.0001465097,0.00008286859],"category_scores_gemma":[0.001169215,0.00013894,0.0002760845,0.0002135642,0.0002764551,0.0002054031,0.0001823256,0.0007154748,0.000001058968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009862165,"about_ca_system_score_gemma":0.0001184331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000556224,"about_ca_topic_score_gemma":0.00003468416,"domain_scores_codex":[0.9982538,0.000173277,0.0009244897,0.0001590363,0.0002393065,0.0002501316],"domain_scores_gemma":[0.9977129,0.001063943,0.0002894926,0.000346189,0.00051213,0.00007535348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003583855,0.001284998,0.320164,0.01350944,0.003635023,0.00007427793,0.01281863,0.1736543,0.006478978,0.0508211,0.1299268,0.2840487],"study_design_scores_gemma":[0.001505763,0.0001264235,0.02034842,0.001289184,0.0003534496,0.0001454386,0.001809487,0.9295874,0.0008898103,0.04067652,0.002939041,0.0003290861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4810425,0.009339301,0.3250279,0.01651448,0.006142659,0.004281013,0.002415206,0.0005053898,0.1547315],"genre_scores_gemma":[0.9907511,0.00008840749,0.007887543,0.0000682265,0.00008075369,0.00001131911,0.000002380835,0.00002282361,0.0010874],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7559331,"threshold_uncertainty_score":0.5665808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01034554862733821,"score_gpt":0.2398684073727708,"score_spread":0.2295228587454326,"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."}}