{"id":"W3083888421","doi":"10.1101/2020.09.07.285502","title":"Automated detection of Hainan gibbon calls for passive acoustic monitoring","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Animal Vocal Communication and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Global Affairs Canada; African Institute for Mathematical Sciences; Division of Mathematical Sciences; Government of Canada; Universiteit Stellenbosch; National Research Foundation; International Development Research Centre","keywords":"Spectrogram; Bioacoustics; Preprocessor; Computer science; Convolutional neural network; Classifier (UML); Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Telecommunications","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001724274,0.0003395369,0.0003708838,0.0000775718,0.0001159849,0.00004841176,0.0004917019,0.0005802131,0.000002905118],"category_scores_gemma":[0.0003237502,0.0003769352,0.000199879,0.0001615097,0.0000911329,0.000005785573,0.0004706119,0.0003295403,0.00000550901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007876842,"about_ca_system_score_gemma":0.0002633671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002471765,"about_ca_topic_score_gemma":0.000002454939,"domain_scores_codex":[0.9984016,0.00008972906,0.0004369977,0.0006161412,0.0001709422,0.0002846073],"domain_scores_gemma":[0.9979632,0.00002565894,0.0004249834,0.0008576532,0.000566232,0.0001622379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009509558,0.00008180629,0.0009086478,0.0002589626,0.00008114725,0.000002430753,0.000003776874,0.00006931373,0.99839,0.00001564873,0.00008155801,0.00001164923],"study_design_scores_gemma":[0.0003640825,0.0002421428,0.0498246,0.0001263262,0.0001396805,1.003199e-8,0.000005782685,0.001215153,0.9461785,5.56199e-7,0.001528378,0.0003747854],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9780205,0.0005849467,0.01943552,0.0001051024,0.0005611322,0.0008041369,0.0002275718,0.0002583145,0.000002786069],"genre_scores_gemma":[0.9951262,0.0001698699,0.00390725,0.0000493921,0.0003646782,0.0002862086,0.000002489006,0.00008962452,0.000004280145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05221146,"threshold_uncertainty_score":0.9998683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02384141398798142,"score_gpt":0.268789056748309,"score_spread":0.2449476427603276,"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."}}