{"id":"W2808753708","doi":"10.1109/joe.2018.2838939","title":"DeepCaustics: Classification and Removal of Caustics From Underwater Imagery","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Oceanic Engineering","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Caustic (mathematics); Artificial intelligence; Underwater; Convolutional neural network; Computer vision; Computer science; Projection (relational algebra); Artificial neural network; Pixel; Geology; Mathematics; Algorithm; Geometry","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":[0.0002387213,0.00007349325,0.0001412978,0.00004832819,0.00003048035,0.00002347162,0.00008257803,0.00004391718,0.00009086596],"category_scores_gemma":[0.00005988819,0.00005518324,0.0000328156,0.00006686323,0.00004068001,0.0001484291,0.000002980316,0.0001194362,0.000007179981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004698533,"about_ca_system_score_gemma":0.0000174256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003072732,"about_ca_topic_score_gemma":0.00001886121,"domain_scores_codex":[0.9993948,0.00001841626,0.0002659071,0.00006613454,0.0001435036,0.0001112772],"domain_scores_gemma":[0.9995362,0.0001114641,0.000123317,0.00006496709,0.0000914458,0.00007264284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004273696,0.00009790248,0.462858,0.0004611932,0.0006878315,0.0009342497,0.004279697,0.03906857,0.4248876,0.0001615052,0.003862355,0.06227375],"study_design_scores_gemma":[0.0004509635,0.0003043807,0.8579818,0.0002194674,0.0001019962,0.0006385003,0.0004388241,0.1299515,0.008386384,0.00019637,0.001091742,0.0002380803],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9887155,0.0005803523,0.00979085,0.00002099572,0.0006449668,0.00001742556,0.00001476425,0.000008440927,0.0002066581],"genre_scores_gemma":[0.9907753,0.00009471922,0.008631028,0.00001280505,0.0004455014,1.298127e-8,0.000003399395,0.000003314757,0.00003394325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4165012,"threshold_uncertainty_score":0.2250307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02419435474907592,"score_gpt":0.215743667485117,"score_spread":0.1915493127360411,"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."}}