{"id":"W7117360416","doi":"10.2139/ssrn.5974794","title":"A Semantic Edge-Aware Tracking Framework for Embedded Maritime Surveillance Systems","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Maritime Navigation and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Segmentation; Object detection; Deep learning; Benchmark (surveying); Categorization; Robustness (evolution); Identification (biology); Reliability (semiconductor)","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":[0.000560124,0.0009285785,0.0008938441,0.0009639817,0.000555959,0.001730576,0.001740263,0.001139718,0.002141293],"category_scores_gemma":[0.000935082,0.0005338803,0.001063491,0.0009726653,0.0003533325,0.001998356,0.001851587,0.001190817,0.0009772596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004758872,"about_ca_system_score_gemma":0.0009578956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01019218,"about_ca_topic_score_gemma":0.01452814,"domain_scores_codex":[0.9996171,0.0000483563,0.00002754628,0.000113575,0.0001393522,0.00005406391],"domain_scores_gemma":[0.9997013,0.00006406396,0.00002580745,0.00007687815,0.0001038957,0.00002794984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007702307,0.0003503153,0.002277793,0.0006346921,0.0002559996,0.0006581981,0.0004075877,0.3340602,0.06460651,0.05700376,0.01925282,0.5197219],"study_design_scores_gemma":[0.00001607155,0.00004434882,0.0003248941,0.00002590987,0.00004663412,0.00008562117,0.0000386331,0.9697444,0.009167513,0.0115005,0.008983216,0.00002230639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004289938,0.0002721067,0.9900854,0.00004368725,0.00003811051,0.00004410504,0.0002635789,0.003963035,0.001000117],"genre_scores_gemma":[0.2134675,0.0005684841,0.7806025,0.0001306493,0.00004467787,0.00009910923,0.001675849,0.0005436682,0.00286758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01019218,"threshold_uncertainty_score":0.0202657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0115665884106757,"score_gpt":0.2680516145658612,"score_spread":0.2564850261551855,"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."}}