{"id":"W4396625970","doi":"10.3390/environments11050094","title":"Assessing the Interpretability–Performance Trade-Off of Artificial Neural Networks Using Sentinel Fish Health Data","year":2024,"lang":"en","type":"article","venue":"Environments","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Environment and Protected Areas; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Environment and Parks","keywords":"Interpretability; Artificial neural network; Machine learning; Computer science; Artificial intelligence; Proxy (statistics); Ecology; Data mining; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003868762,0.0001048626,0.0001194277,0.00002088005,0.0001932539,0.0002332085,0.0009640195,0.00002786659,0.000007925313],"category_scores_gemma":[0.000003727303,0.00007758706,0.00003849176,0.0002265371,0.0000923944,0.0008025186,0.0005896484,0.0002088066,0.000003238958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003505731,"about_ca_system_score_gemma":0.00002106195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007189379,"about_ca_topic_score_gemma":0.000001540006,"domain_scores_codex":[0.9987828,0.00008283734,0.0003132159,0.0003966103,0.0001906621,0.0002339007],"domain_scores_gemma":[0.9988337,0.00008728799,0.00009160416,0.0009373348,0.000001323076,0.00004882035],"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":[0.000002549591,0.0001460826,0.003987502,0.00004917073,0.00003661311,0.000003630333,0.0003886193,0.08463804,0.001405349,0.0006566458,0.002177685,0.9065081],"study_design_scores_gemma":[0.00002462043,0.00001013504,0.0114068,0.00003801876,0.00000645404,0.000006755744,0.00001200367,0.9848628,0.00008635919,0.00005667251,0.00342091,0.0000684487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4580855,0.0005662669,0.5371698,0.003406073,0.0004795213,0.0002001037,0.00001000659,0.00004898912,0.00003374946],"genre_scores_gemma":[0.9978451,0.00007615829,0.001318312,0.0005506059,0.0001624346,0.000005013425,0.00001941939,0.00000952788,0.0000134873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9064397,"threshold_uncertainty_score":0.3163908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06129989081271294,"score_gpt":0.3264110105046933,"score_spread":0.2651111196919804,"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."}}