{"id":"W4399761989","doi":"10.1098/rsos.240271","title":"Identifying prey capture events of a free-ranging marine predator using bio-logger data and deep learning","year":2024,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Global Affairs Canada; African Institute for Mathematical Sciences; Norges Forskningsråd; North-West University; Antarctic Wildlife Research Fund; Carnegie Corporation of New York; International Development Research Centre; Division of Mathematical Sciences; Government of Canada","keywords":"Predation; Foraging; Marine ecosystem; Convolutional neural network; Computer science; Prey detection; Data logger; Ecology; Artificial intelligence; Ecosystem; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00208971,0.0001714181,0.0002268864,0.00002169693,0.0006560796,0.0003868944,0.002901326,0.00004999936,0.0009477264],"category_scores_gemma":[0.0002264589,0.0001491453,0.00006051526,0.000877369,0.0006348367,0.001343463,0.02844708,0.0002384369,0.0000295989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001992556,"about_ca_system_score_gemma":0.0000530444,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008257581,"about_ca_topic_score_gemma":0.0008648591,"domain_scores_codex":[0.9976329,0.00004499407,0.0002605459,0.0009220335,0.0007012168,0.0004383422],"domain_scores_gemma":[0.9990767,0.00005865772,0.0001000814,0.0006198121,0.00001934131,0.0001253598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001508745,0.00008369119,0.9118683,0.0004511974,0.0001023887,0.00001599531,0.006131564,0.001569613,0.009295396,0.0001747948,0.002461577,0.06783035],"study_design_scores_gemma":[0.0003246996,0.00005006142,0.2453311,0.0002490664,0.00008880737,0.00001607994,0.001596876,0.7429243,0.0003603121,0.0003224651,0.008321499,0.0004147016],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.983955,0.001512099,0.003778496,0.0001589103,0.0002263744,0.0005992744,0.00002904744,0.00006053739,0.009680256],"genre_scores_gemma":[0.9700006,0.0002045593,0.0285388,0.0001168191,0.00003255583,0.000007525145,0.000007915712,0.00001884879,0.001072434],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7413547,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03729971734976031,"score_gpt":0.3084836407045673,"score_spread":0.271183923354807,"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."}}