{"id":"W3191911242","doi":"10.1007/978-3-030-84060-0_19","title":"On the Trustworthiness of Tree Ensemble Explainability Methods","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Georgian College","funders":"","keywords":"Computer science; Feature (linguistics); Stability (learning theory); Trustworthiness; Machine learning; Tree (set theory); Focus (optics); Artificial intelligence; Variety (cybernetics); Measure (data warehouse); Ensemble learning; Random forest; Data mining; Noise (video); Computer security; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03151485,0.001148467,0.002001905,0.003568869,0.001462484,0.002980042,0.002361925,0.002669915,0.003349413],"category_scores_gemma":[0.1855866,0.0008079265,0.002062693,0.002230728,0.003452734,0.007046079,0.00410058,0.005316135,0.0004678288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00205649,"about_ca_system_score_gemma":0.001330837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002870719,"about_ca_topic_score_gemma":0.002237832,"domain_scores_codex":[0.9799492,0.01200057,0.0009714503,0.001936617,0.004622808,0.0005193701],"domain_scores_gemma":[0.6458458,0.3215289,0.006140231,0.01560114,0.009394127,0.001489792],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008763492,0.0001785384,0.01622055,0.0005939458,0.0008947803,0.0002177873,0.0009248597,0.4208955,0.001972101,0.3138293,0.005829255,0.237567],"study_design_scores_gemma":[0.00002648786,0.00007708837,0.001164388,0.0001057144,0.00005886887,0.00004627736,0.0000485225,0.8199039,0.0006080861,0.1771876,0.0007556596,0.00001745273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05094775,0.002723382,0.9380016,0.001550549,0.0001583043,0.00009976149,0.0002265643,0.0003817122,0.005910394],"genre_scores_gemma":[0.7669291,0.001585261,0.2260612,0.0005150887,0.0007483565,0.0002501293,0.0008497877,0.0004235548,0.002637604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9684852,"threshold_uncertainty_score":0.1666684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04130715168566368,"score_gpt":0.3148927649232393,"score_spread":0.2735856132375756,"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."}}