{"id":"W4413452014","doi":"10.1016/j.ecoinf.2025.103396","title":"Advances in deep learning-driven photo identification and meta analysis of cetaceans in large data repositories","year":2025,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Arctic Eider Society; Fisheries and Oceans Canada","funders":"Northwest Fisheries Science Center; National Marine Fisheries Service; Friedrich-Alexander-Universität Erlangen-Nürnberg","keywords":"Identification (biology); Data science; Computer science; Deep learning; World Wide Web; Artificial intelligence; Ecology; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004895146,0.00007505839,0.0003790999,0.00007637595,0.00005324807,0.00001963673,0.000270312,0.0000450673,0.0004447817],"category_scores_gemma":[0.0002880849,0.00005733812,0.00004374892,0.0009010119,0.00008343218,0.0004830949,0.001031482,0.0001079411,0.000006863719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005225688,"about_ca_system_score_gemma":0.000002648468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001157107,"about_ca_topic_score_gemma":0.01701656,"domain_scores_codex":[0.9990551,0.00005225417,0.0005158956,0.0001241167,0.0001189439,0.0001336797],"domain_scores_gemma":[0.9994349,0.0001424045,0.0001716506,0.0002261711,0.000007269292,0.00001760279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006659149,0.00009651692,0.9891514,0.00005300099,0.0005344105,0.000001297524,0.0005992906,0.008151655,0.000004846535,0.000309437,0.00005231935,0.001039233],"study_design_scores_gemma":[0.0001015815,0.00002826178,0.9165215,0.00000161598,0.001990095,1.373004e-7,0.0007080741,0.07269729,0.00001221805,0.0001062405,0.007771158,0.00006181315],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9717961,0.001015497,0.0008595352,0.0001269373,0.00003248078,0.0003092198,0.00002092912,0.00001781148,0.02582151],"genre_scores_gemma":[0.9973259,0.001438367,0.0009453431,0.0001121834,0.000001139142,0.00001637162,0.00002995576,0.000001102766,0.0001296381],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07262982,"threshold_uncertainty_score":0.9495639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02590353789239536,"score_gpt":0.2947104760958523,"score_spread":0.268806938203457,"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."}}