{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05116939,0.002605322,0.002148814,0.003559792,0.001535795,0.0047899,0.002744859,0.003012491,0.002137868],"category_scores_gemma":[0.2442021,0.001288223,0.003071967,0.001629261,0.006899494,0.005177001,0.005816371,0.005573013,0.000406619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00226655,"about_ca_system_score_gemma":0.001559679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005447722,"about_ca_topic_score_gemma":0.001976855,"domain_scores_codex":[0.9781026,0.01476539,0.001122316,0.002902598,0.002361543,0.0007455833],"domain_scores_gemma":[0.6121187,0.3548847,0.01031271,0.01736921,0.0042122,0.00110253],"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":[0.0003876398,0.00008311501,0.02020034,0.0003389109,0.001137592,0.0003200761,0.0004374291,0.8660434,0.00139797,0.0866857,0.001104187,0.02186368],"study_design_scores_gemma":[0.00003118804,0.0001276139,0.002382515,0.0001360004,0.0001124605,0.00007678973,0.00008279702,0.8360702,0.00101657,0.1590791,0.0008273633,0.00005746735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2060789,0.003292572,0.7688796,0.006820745,0.0003077209,0.0001840298,0.0008754786,0.001266345,0.0122945],"genre_scores_gemma":[0.9605004,0.0009837857,0.03533852,0.000715818,0.0003570587,0.0001606671,0.0006747451,0.0003478625,0.000921113],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05116939,"threshold_uncertainty_score":0.2706128,"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."}}