{"id":"W4307576169","doi":"10.1002/env.2772","title":"An illustration of model agnostic explainability methods applied to environmental data","year":2022,"lang":"en","type":"article","venue":"Environmetrics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"National Institute of Environmental Health Sciences; National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Variety (cybernetics); Focus (optics); Artificial intelligence; Transparency (behavior); Inference; Implementation; Machine learning; Deep learning; Feature (linguistics); Data science","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":[0.00232976,0.0001782237,0.0002289916,0.0003817644,0.0003337002,0.00005016366,0.003147902,0.00005358888,0.0001416453],"category_scores_gemma":[0.0003360046,0.0002099103,0.00004152611,0.001240635,0.00009611864,0.0007202489,0.002455863,0.0002498934,0.00004244623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000305687,"about_ca_system_score_gemma":0.00005770456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004315591,"about_ca_topic_score_gemma":0.000003697512,"domain_scores_codex":[0.9972427,0.0003371047,0.0004653098,0.0009078485,0.0006932049,0.0003538636],"domain_scores_gemma":[0.9963585,0.0004312322,0.0001647171,0.002847918,0.000008008547,0.0001896817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001596359,0.0006084715,0.0004085608,0.000007529553,0.000008184005,0.000005131659,0.001600503,0.799154,0.04885871,0.01161537,0.0002049594,0.1375126],"study_design_scores_gemma":[0.00008401029,0.0002968021,0.001652218,7.990612e-7,0.00001294443,0.000004400833,0.0007326931,0.9450347,0.04223137,0.006347904,0.003304611,0.0002974835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09450806,0.00006160945,0.9042636,0.0001458677,0.0001290719,0.0004113877,0.00009864161,0.00005730883,0.0003244552],"genre_scores_gemma":[0.6690558,0.00001052324,0.3305567,0.0001774576,0.00001730491,0.00005495564,0.00006798257,0.00001284871,0.00004639211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5745478,"threshold_uncertainty_score":0.8559895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112185857957852,"score_gpt":0.3504425054411345,"score_spread":0.2382566474832826,"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."}}