{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002617613,0.0001169798,0.0001330601,0.00005673168,0.000111707,0.00001361561,0.0004296473,0.0001008554,0.00001370628],"category_scores_gemma":[0.0002706473,0.00007641677,0.00004619773,0.00026391,0.000175884,0.000002559407,0.0004258939,0.0001359203,0.00003994769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001301051,"about_ca_system_score_gemma":0.00006722212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001763048,"about_ca_topic_score_gemma":0.0003771548,"domain_scores_codex":[0.9990585,0.000156102,0.0002776018,0.0002486117,0.00005626986,0.0002029389],"domain_scores_gemma":[0.999111,0.000258716,0.00009481911,0.0003835242,0.0001050618,0.00004690528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002487851,0.0002989531,0.006695339,0.00003457111,0.0001110375,0.00008551232,0.0001938961,0.01586675,0.9427863,0.001673069,0.002902016,0.02910378],"study_design_scores_gemma":[0.009340621,0.006584194,0.3114533,0.0002861689,0.0006886182,0.001924597,0.005459024,0.3856285,0.213145,0.01337396,0.04809244,0.00402361],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942002,0.0001812796,0.003099667,0.001588786,0.00006235001,0.0002999872,0.0005278306,0.00001570215,0.00002415616],"genre_scores_gemma":[0.9949854,0.00003620099,0.002269056,0.0009383487,0.00008431628,0.00005027387,0.001581666,0.00001162475,0.00004308835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7296413,"threshold_uncertainty_score":0.3116185,"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."}}