{"id":"W3187947129","doi":"10.1139/cjfas-2020-0446","title":"Early lessons in deploying cameras and artificial intelligence technology for fisheries catch monitoring: where machine learning meets commercial fishing","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Commonwealth Scientific and Industrial Research Organisation","keywords":"Bycatch; Computer science; Convolutional neural network; Artificial intelligence; Machine learning; Fishing; Fishery","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0142543,0.001466907,0.0006259126,0.002131851,0.001342849,0.006522162,0.002876694,0.005866209,0.004084889],"category_scores_gemma":[0.02126625,0.0009015223,0.0007030556,0.001500161,0.01273047,0.018581,0.002830931,0.01035008,0.002208209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004963335,"about_ca_system_score_gemma":0.003251907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01700223,"about_ca_topic_score_gemma":0.009793845,"domain_scores_codex":[0.9959766,0.001564998,0.0003085366,0.0008672281,0.0009881904,0.0002944529],"domain_scores_gemma":[0.9842445,0.008470786,0.0004593575,0.001192865,0.004619098,0.001013357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003214318,0.0004747049,0.0143128,0.001742458,0.0001148617,0.0007252371,0.003337518,0.01024173,0.006684853,0.2913406,0.04410059,0.6266031],"study_design_scores_gemma":[0.0001120547,0.0008962656,0.01448337,0.003443932,0.00005780357,0.001038335,0.006796256,0.02209127,0.01605031,0.4936669,0.4409654,0.000398115],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.05666086,0.07598568,0.3614959,0.4106015,0.005655675,0.0005286304,0.0005136393,0.001025266,0.08753291],"genre_scores_gemma":[0.4710895,0.07450092,0.3789482,0.03707532,0.004885084,0.0005456944,0.0002924939,0.000666082,0.03199663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01700223,"threshold_uncertainty_score":0.07538486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05634893029415425,"score_gpt":0.2959061218706588,"score_spread":0.2395571915765045,"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."}}