{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003044838,0.0003225614,0.0002719224,0.0001199791,0.0003850106,0.001292059,0.002409063,0.0002065807,0.00002853731],"category_scores_gemma":[0.0002130553,0.0002915953,0.00009749954,0.0007291168,0.0001302163,0.006327083,0.0002630649,0.0006720266,0.0002104385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001409752,"about_ca_system_score_gemma":0.000133543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001410208,"about_ca_topic_score_gemma":0.00289075,"domain_scores_codex":[0.9976599,0.0001014449,0.0002892234,0.001268745,0.0002382861,0.0004424221],"domain_scores_gemma":[0.9962873,0.0007559645,0.00006697805,0.002690597,0.00009427701,0.0001048305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004845089,0.00159066,0.004888052,0.000591853,0.001503027,0.000805142,0.02378074,0.001678158,0.009720583,0.1771602,0.07676279,0.7010343],"study_design_scores_gemma":[0.0006630708,0.00040895,0.002410416,0.001911589,0.0003410976,0.0001394918,0.00189166,0.5436649,0.03332398,0.1370238,0.2763359,0.001885208],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008634987,0.008707508,0.9740537,0.004713938,0.001665415,0.0003145796,0.001048774,0.0003638333,0.0004972343],"genre_scores_gemma":[0.9754582,0.0006251948,0.02189193,0.0002971851,0.0002111549,0.00004452325,0.0006619935,0.00003575359,0.0007740653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9668232,"threshold_uncertainty_score":0.9999536,"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."}}