{"id":"W1999244377","doi":"10.1109/oceanssyd.2010.5603995","title":"Towards generalized benthic species recognition and quantification using computer vision","year":2010,"lang":"en","type":"article","venue":"OCEANS'10 IEEE SYDNEY","topic":"Ichthyology and Marine Biology","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; University of Victoria","keywords":"Benthic zone; Underwater; Computer science; Seabed; Benthic habitat; Scale (ratio); Submarine pipeline; Feature (linguistics); Artificial intelligence; Marine engineering; Remote sensing; Oceanography; Geology; Geography; Engineering; Cartography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002967632,0.0001204464,0.0001274928,0.00003873774,0.0001655791,0.00002571184,0.0001092259,0.0001876734,0.003192617],"category_scores_gemma":[0.00002975251,0.0001062545,0.000032296,0.00008215516,0.000323404,0.000152062,0.00008984493,0.0001810871,0.0005740674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002597049,"about_ca_system_score_gemma":0.000009976747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001862083,"about_ca_topic_score_gemma":0.0002113212,"domain_scores_codex":[0.999144,0.00007879255,0.0001680519,0.0003097712,0.0001036577,0.0001957707],"domain_scores_gemma":[0.999638,0.00002651483,0.00006444682,0.0001777832,0.00001535918,0.00007794385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001160029,0.0001217375,0.01738241,0.00001450853,0.00001969825,0.000008786744,0.0003199665,0.00009101836,0.9022529,0.0003684923,0.01015713,0.06914732],"study_design_scores_gemma":[0.002291203,0.0006876039,0.6844824,0.00004119024,0.0001492228,0.0003645639,0.00005769411,0.04397116,0.08547036,0.00760463,0.1736395,0.001240464],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928176,0.000009298065,0.00307144,0.0003637078,0.001155831,0.0001291217,0.00001119605,0.00004070864,0.002401069],"genre_scores_gemma":[0.988554,0.00005231559,0.009695397,0.0004264414,0.0002665877,0.000003376856,0.00009150306,0.00001207856,0.0008982955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8167826,"threshold_uncertainty_score":0.9977186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03482301368972434,"score_gpt":0.2637205757730542,"score_spread":0.2288975620833299,"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."}}