{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004108205,0.0005717839,0.0007671275,0.0005345386,0.0003640047,0.0004112325,0.00522563,0.0003269477,0.00008085006],"category_scores_gemma":[0.001346722,0.0004168595,0.0002714693,0.00140957,0.00123677,0.0004909822,0.001806887,0.001056719,0.00002580007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003239824,"about_ca_system_score_gemma":0.0008697195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006494448,"about_ca_topic_score_gemma":0.000221674,"domain_scores_codex":[0.9951353,0.0003074909,0.0008454542,0.001766238,0.001208433,0.0007370784],"domain_scores_gemma":[0.9906421,0.004813071,0.0004519306,0.003251051,0.0006959773,0.0001458271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006977897,0.0000462735,0.00001202728,0.00003357721,0.00001007873,0.00005412086,0.001023666,0.01649053,0.0006050612,0.3975194,0.00001564877,0.5841826],"study_design_scores_gemma":[0.00006413291,0.0001878738,0.00004882064,0.0003031399,0.000007627393,0.0000279052,0.000002245348,0.2326061,0.09109135,0.6745309,0.0006563635,0.0004735561],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005293229,0.0003696143,0.985951,0.002160951,0.00167727,0.0004799833,0.000002188964,0.00009175851,0.008737926],"genre_scores_gemma":[0.2646533,0.00004992168,0.7316937,0.002341264,0.0003146862,0.00003604596,0.000002725608,0.00005074998,0.0008575553],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5837091,"threshold_uncertainty_score":0.9998283,"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."}}