{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005448675,0.0007527414,0.000584852,0.001535697,0.0007171377,0.001465423,0.001971561,0.001438228,0.004346033],"category_scores_gemma":[0.01855596,0.0003655891,0.001625475,0.001668989,0.00242552,0.002325821,0.003474611,0.003345048,0.0003393521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001197746,"about_ca_system_score_gemma":0.001327379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003824709,"about_ca_topic_score_gemma":0.003492201,"domain_scores_codex":[0.9981254,0.00111587,0.00008704275,0.0002419526,0.0003371083,0.00009261906],"domain_scores_gemma":[0.9906446,0.006538141,0.0006308896,0.001699088,0.0003675993,0.0001197338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006174656,0.00006183536,0.003718375,0.0000747603,0.00007290087,0.0002234461,0.0004704527,0.1806438,0.001052951,0.7696388,0.002583236,0.04139772],"study_design_scores_gemma":[0.00001171519,0.00001648889,0.000447834,0.00001634937,0.00000929777,0.00005226872,0.00003369441,0.6875235,0.0005607246,0.3083903,0.002924383,0.00001331349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008467863,0.0001301422,0.98676,0.001188128,0.00002825923,0.0000275967,0.0001452925,0.0003826094,0.002870127],"genre_scores_gemma":[0.4982691,0.0003489949,0.4969161,0.000569151,0.0001379871,0.0002793845,0.0004206738,0.000369298,0.002689389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005448675,"threshold_uncertainty_score":0.02881569,"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."}}