{"id":"W4404689245","doi":"10.1109/oceans55160.2024.10754192","title":"Detecting Unexpected Marine Species with Underwater Cameras and Deep Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Fisheries and Oceans Canada; Dalhousie University","funders":"Dental Foundation of Oregon","keywords":"Underwater; Computer science; Artificial intelligence; Deep learning; Computer vision; Marine engineering; Environmental science; Geology; Remote sensing; Oceanography; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006819939,0.000073754,0.00004792311,0.00004214172,0.00009190902,0.0001244648,0.00004026914,0.0000424435,0.0002024647],"category_scores_gemma":[0.00001802412,0.00005634617,0.00001727944,0.00008856109,0.00005292761,0.000003509056,0.00004281915,0.00006901358,0.00002994503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000514777,"about_ca_system_score_gemma":0.00001192065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001242425,"about_ca_topic_score_gemma":0.00008423382,"domain_scores_codex":[0.9994909,0.00002301023,0.00009463968,0.0002376064,0.00005798639,0.00009590112],"domain_scores_gemma":[0.9997826,0.000009600117,0.00001812845,0.0001125194,0.00004655842,0.00003057487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002205341,0.00001168206,0.003194794,0.00003606248,0.00007361201,0.000002663662,0.0001992968,0.00003201492,0.9840174,0.003099137,0.000285727,0.009025501],"study_design_scores_gemma":[0.0002133676,0.0001460948,0.01083182,0.00001545458,0.00002373863,0.00006718708,0.001164121,0.001347731,0.7666022,0.00003542759,0.2193213,0.0002315673],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9537733,0.0004601609,0.02416733,0.0003556652,0.0001139616,0.00009388671,0.000001072752,0.0001001986,0.02093448],"genre_scores_gemma":[0.9679676,0.00009980832,0.0008049498,0.00004755645,0.00007078742,0.000008731799,0.00006706572,0.00001478525,0.03091871],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2190355,"threshold_uncertainty_score":0.229773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01098653764917748,"score_gpt":0.2337106571870571,"score_spread":0.2227241195378796,"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."}}