{"id":"W4365457226","doi":"10.1371/journal.pcbi.1010325","title":"Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls","year":2023,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Animal Vocal Communication and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Social Sciences and Humanities Research Council of Canada; Ministère de l'Enseignement Supérieur et de la Recherche (Luxembourg); LabEx ASLAN; Université de Lyon; Institut Universitaire de France; Agence Nationale de la Recherche; Université du Québec à Chicoutimi","keywords":"Bonobo; Computer science; Workflow; Artificial intelligence; Robustness (evolution); Feature vector; Machine learning; Support vector machine; Cluster analysis; Feature (linguistics); Pattern recognition (psychology); Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00476739,0.001684724,0.001164104,0.001742957,0.001586961,0.002476267,0.001977896,0.001813534,0.004995625],"category_scores_gemma":[0.01623988,0.0005687727,0.001753325,0.001197061,0.001192052,0.00231556,0.003464008,0.002615511,0.006646277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005481735,"about_ca_system_score_gemma":0.001702017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004550222,"about_ca_topic_score_gemma":0.0076399,"domain_scores_codex":[0.9971012,0.0006778787,0.0002414961,0.001072112,0.0006396896,0.0002675023],"domain_scores_gemma":[0.9944409,0.001809016,0.00034278,0.001530502,0.001501911,0.0003748716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001325124,0.000559134,0.0265559,0.0006000056,0.0003702437,0.0008528291,0.002497407,0.04019006,0.09739611,0.004507191,0.02394729,0.8011987],"study_design_scores_gemma":[0.0001377442,0.0003198484,0.02036774,0.0001376382,0.00009411565,0.0005348179,0.001837252,0.8523134,0.0786471,0.02199792,0.02344376,0.0001686909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08545208,0.00028326,0.8530719,0.0007595439,0.0003019935,0.0003716225,0.001688833,0.05641215,0.00165852],"genre_scores_gemma":[0.159895,0.00009761301,0.8299707,0.0003339102,0.00006806725,0.0004375288,0.004228103,0.003085184,0.001883898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004995625,"threshold_uncertainty_score":0.02521265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03834006191966119,"score_gpt":0.3051991602154638,"score_spread":0.2668590982958026,"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."}}