{"id":"W4415070077","doi":"10.1016/j.ecoinf.2025.103473","title":"ESC-YOLOv8-seg: A real-time non-destructive detection framework for small-target surface anomalies in zebrafish underwater monitoring","year":2025,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Agriculture","funders":"National Key Research and Development Program of China; Key Technology Research and Development Program of Shandong; Ministry of Agriculture and Rural Affairs of the People's Republic of China; Department of Science and Technology of Shandong Province","keywords":"Zebrafish; Danio; Fish <Actinopterygii>; Underwater; Aquaculture; Activity detection; Range (aeronautics)","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":[0.0005732145,0.0002514127,0.0003488947,0.00009688402,0.0002112838,0.0001121578,0.0004989221,0.000504994,0.00007704557],"category_scores_gemma":[0.0004948165,0.0002131724,0.00008324416,0.0004553424,0.0002738193,0.000414489,0.0005969903,0.0004083422,0.0001685643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006815497,"about_ca_system_score_gemma":0.0000159238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009999043,"about_ca_topic_score_gemma":0.00002489222,"domain_scores_codex":[0.9982986,0.000056934,0.0006593771,0.000242472,0.0001763595,0.0005662371],"domain_scores_gemma":[0.9988161,0.0005794728,0.0001795292,0.0003472316,0.0000210164,0.00005665703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003831449,0.000740679,0.867201,0.0004778795,0.0001772618,0.00002130297,0.00885521,0.0691479,0.04072345,0.003389486,0.0008188468,0.008063846],"study_design_scores_gemma":[0.0008386978,0.0005525275,0.5896243,0.0001552227,0.00003029839,0.000004350152,0.004147832,0.01617429,0.1899759,0.1972232,0.0006034643,0.0006698251],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9758858,0.000002992602,0.02036935,0.0002807985,0.0004468015,0.000675922,0.00000749892,0.0003339747,0.001996841],"genre_scores_gemma":[0.752161,0.0000117738,0.2474587,0.00005179745,0.00002458185,0.00009285622,0.000003840264,0.000009611738,0.0001858596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2775767,"threshold_uncertainty_score":0.869292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02185371563812187,"score_gpt":0.2678142059781903,"score_spread":0.2459604903400684,"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."}}