{"id":"W4392857185","doi":"10.22541/essoar.171052510.02996233/v1","title":"On Robustness of the Explanatory Power of Machine Learning Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Suncor Energy Incorporated","keywords":"Computer science; Machine learning; Robustness (evolution); Artificial intelligence; Explanatory power; Decision tree; Predictive power; Suite; Hyperparameter; Random forest; Initialization; Data mining","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":[0.0005572229,0.0002252619,0.0003273131,0.0001968806,0.0000572639,0.00006923852,0.002180873,0.0001763521,0.00008505418],"category_scores_gemma":[0.0000897522,0.0001520782,0.0002257161,0.0003309279,0.00009737386,0.0001143519,0.003697019,0.0009671379,0.00002683256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005968628,"about_ca_system_score_gemma":0.0002084586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003516229,"about_ca_topic_score_gemma":0.00005118831,"domain_scores_codex":[0.9980713,0.0001509786,0.0004779609,0.0005357448,0.0005392456,0.0002247608],"domain_scores_gemma":[0.9980468,0.0002014365,0.0002557648,0.001271263,0.0001787932,0.00004597898],"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":[0.000004012305,0.00003609518,0.000009531363,0.0001048522,0.00002362469,0.000003329674,0.001001637,0.640438,0.0001221818,0.3571427,0.0002746874,0.0008392864],"study_design_scores_gemma":[0.00001775749,0.0000423036,0.000006359468,0.0002822877,0.000008488432,0.000001742449,0.0001346078,0.821083,0.03395129,0.1442562,0.00007035505,0.0001455518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1224395,0.0008385672,0.828854,0.001200944,0.002959024,0.0004834349,0.0000132281,0.0002469968,0.04296429],"genre_scores_gemma":[0.9945671,0.00002219303,0.003325423,0.00007066369,0.00002593552,0.00001536777,0.000001320023,0.00001975267,0.001952246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8721276,"threshold_uncertainty_score":0.620157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04586587803864699,"score_gpt":0.2670253616480706,"score_spread":0.2211594836094236,"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."}}