{"id":"W4391026313","doi":"10.1145/3641108","title":"Interpreting Deep Forest through Feature Contribution and MDI Feature Importance","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Interpretability; Categorical variable; Feature (linguistics); Random forest; Computer science; Tree (set theory); Artificial intelligence; Variety (cybernetics); Feature model; Data mining; Layer (electronics); Machine learning; Pattern recognition (psychology); Mathematics; Software","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":[],"consensus_categories":[],"category_scores_codex":[0.00291983,0.0008387495,0.0006601466,0.002015786,0.0005450215,0.001322347,0.001459462,0.0009185467,0.001363619],"category_scores_gemma":[0.01267661,0.0004030963,0.000605987,0.001176991,0.001235656,0.00313847,0.001875747,0.001915853,0.0002765679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001021225,"about_ca_system_score_gemma":0.0009711304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003596465,"about_ca_topic_score_gemma":0.005124371,"domain_scores_codex":[0.99921,0.0002474354,0.0000457223,0.0001967903,0.0002105772,0.000089357],"domain_scores_gemma":[0.9953935,0.002869468,0.0004247228,0.0005264149,0.0006342753,0.0001516439],"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":[0.00023408,0.0001565961,0.02214518,0.0002518524,0.0001128451,0.0003884978,0.0004257333,0.4774155,0.00865249,0.1148135,0.004986024,0.3704177],"study_design_scores_gemma":[0.000007325226,0.00001581593,0.001080181,0.00001605203,0.00001309525,0.00005050493,0.00002356094,0.9366219,0.001598621,0.05986723,0.0006939699,0.00001177496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02730687,0.0002639818,0.970561,0.000287015,0.00003116623,0.00003579173,0.0001126013,0.0004712312,0.0009303527],"genre_scores_gemma":[0.6904657,0.0003182907,0.3067762,0.0002045295,0.0000904221,0.000113755,0.0004979827,0.0001829947,0.001350084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003596465,"threshold_uncertainty_score":0.01544166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03162727012661239,"score_gpt":0.3094050055243785,"score_spread":0.2777777353977661,"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."}}