{"id":"W4403921649","doi":"10.2139/ssrn.5004880","title":"Enhanced Underwater Image Dehazing Using an Improved Dark Channel Prior Method","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Underwater; Channel (broadcasting); Image (mathematics); Computer science; Computer vision; Artificial intelligence; Geology; Telecommunications; Oceanography","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":[0.0002775211,0.0006267647,0.000428197,0.0006764402,0.0002040961,0.0005740468,0.0003988533,0.000565152,0.002974135],"category_scores_gemma":[0.0008871931,0.0003110307,0.0004517772,0.0005275891,0.0003782472,0.0009746876,0.000845117,0.001031158,0.0008780645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001977663,"about_ca_system_score_gemma":0.0006007577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001295578,"about_ca_topic_score_gemma":0.00257432,"domain_scores_codex":[0.999809,0.00001829413,0.000008885171,0.0000312322,0.0001148283,0.00001779832],"domain_scores_gemma":[0.9996315,0.00008616802,0.00003240373,0.00007162121,0.0001577276,0.00002051338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003148045,0.0001603308,0.0008948991,0.0003686734,0.00006660086,0.0001735108,0.0001476279,0.03086576,0.5355876,0.008725538,0.002330263,0.4203644],"study_design_scores_gemma":[0.00003878632,0.000173703,0.003946808,0.00005488172,0.0001238299,0.0009170221,0.00007542265,0.5467329,0.4280425,0.003147015,0.01666604,0.00008110706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02755175,0.0004347841,0.9679602,0.000144936,0.00008696006,0.00004114516,0.00008816284,0.0003726883,0.003319479],"genre_scores_gemma":[0.2026566,0.00155097,0.7764496,0.0001360305,0.00009142147,0.00006623209,0.0003361263,0.0002671045,0.01844599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002974135,"threshold_uncertainty_score":0.009949446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01928009676285629,"score_gpt":0.3193430172909612,"score_spread":0.3000629205281049,"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."}}