{"id":"W4414947457","doi":"10.1007/s12145-025-02033-2","title":"Benchmarking coastal boundary datasets in deep learning applications","year":2025,"lang":"en","type":"article","venue":"Earth Science Informatics","topic":"Coastal and Marine Dynamics","field":"Earth and Planetary Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmarking; Deep learning; Workflow; Metric (unit); Boundary (topology); Flexibility (engineering); Standardization","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":[0.0006838356,0.00009973766,0.000109038,0.0003505929,0.0004993802,0.0002797068,0.0004308485,0.00003124703,0.000195898],"category_scores_gemma":[0.00007419171,0.00009038413,0.00002235705,0.001513607,0.0003830834,0.001067271,0.0001351048,0.0002487899,0.0001104372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005934654,"about_ca_system_score_gemma":0.0002725904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006233664,"about_ca_topic_score_gemma":0.01682943,"domain_scores_codex":[0.9988189,0.0000132777,0.0003432181,0.0001342165,0.0003173388,0.0003730984],"domain_scores_gemma":[0.9994949,0.00008558687,0.00008283376,0.0002043422,0.0000407903,0.00009152319],"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":[0.000005175042,0.000009874832,0.2723576,0.00003493836,0.000001820936,0.000001832817,0.0004445194,0.02120611,0.00000617395,0.0008717286,0.00003591157,0.7050243],"study_design_scores_gemma":[0.000145417,0.0000331189,0.3429852,0.00002549156,0.000003091614,0.000007642932,0.00090459,0.5755532,0.00001310288,0.0007187595,0.07947884,0.0001314647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6077427,0.0001571426,0.06973137,0.0002389904,0.0008478702,0.0008713845,0.0003287829,0.0001781691,0.3199036],"genre_scores_gemma":[0.9889523,0.00004693464,0.009753364,0.0003003023,0.00002815699,0.00000346302,0.000605751,0.000001218527,0.0003084516],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7048929,"threshold_uncertainty_score":0.9391218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00487903907673902,"score_gpt":0.2199935137247885,"score_spread":0.2151144746480494,"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."}}