{"id":"W4408824736","doi":"10.5194/oos2025-998","title":"Applications of Computer Vision in Underwater Ecology: A Case Study from the Northeast Pacific","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Underwater; Ecology; Oceanography; Geography; Biology; Geology","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":[0.0008282429,0.0004075877,0.0002417128,0.001335925,0.002502156,0.0008567211,0.0007854997,0.0006494834,0.0006224269],"category_scores_gemma":[0.002695457,0.0001907679,0.0001863464,0.002856767,0.0008824953,0.0005229035,0.0008062284,0.0004658368,0.0001097567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003676608,"about_ca_system_score_gemma":0.003001963,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.6203994,"about_ca_topic_score_gemma":0.8480178,"domain_scores_codex":[0.9994388,0.000127035,0.00003400626,0.00008269833,0.0002236868,0.00009383397],"domain_scores_gemma":[0.9981919,0.0006735523,0.0001420224,0.00009864927,0.0007180177,0.000175803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002438579,0.001089548,0.5454519,0.000827476,0.00011505,0.04641627,0.06135953,0.01227241,0.01623449,0.001502615,0.006459622,0.3080272],"study_design_scores_gemma":[0.00002478768,0.0003074964,0.859217,0.0002110989,0.00007366794,0.005827121,0.08336597,0.02203982,0.004926746,0.0007869544,0.02315201,0.00006734135],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920136,0.0002951747,0.002237733,0.0004572388,0.000006088089,0.000140274,0.0001887732,0.00003254271,0.004628627],"genre_scores_gemma":[0.9840406,0.0009940427,0.01115945,0.000131387,0.00001133018,0.00005049286,0.000264927,0.00002343059,0.003324364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6203994,"threshold_uncertainty_score":0.7636722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02713631522037978,"score_gpt":0.294297384385086,"score_spread":0.2671610691647062,"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."}}