{"id":"W3037201993","doi":"","title":"Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Identifiability; Interpretability; Representation (politics); Piecewise; Equivalence (formal languages); Computer science; Decomposition; Algorithm; Additive model; Mathematics; Generalized additive model; Function (biology); Variance (accounting); Artificial intelligence; Machine learning; Discrete 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":[],"consensus_categories":[],"category_scores_codex":[0.0004028498,0.0002750588,0.0002191466,0.0001275944,0.0004707219,0.0009824126,0.0007251321,0.00007283016,0.00007987482],"category_scores_gemma":[0.0002807065,0.0002192043,0.00005100264,0.0002876405,0.0001846087,0.0009374534,0.0001459607,0.0003052494,0.00006740236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000922828,"about_ca_system_score_gemma":0.0001352688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000730301,"about_ca_topic_score_gemma":0.00009651681,"domain_scores_codex":[0.9977751,0.000114674,0.000433981,0.0007323374,0.0005791454,0.0003647143],"domain_scores_gemma":[0.997511,0.0009627704,0.0002260032,0.0002687001,0.000844119,0.0001874518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001548597,0.00008677662,0.000001302126,0.00001142232,0.00004045579,0.00001612679,0.001491346,0.0411347,0.0007081056,0.6192497,0.0002416085,0.3368636],"study_design_scores_gemma":[0.00005274685,0.0006349095,0.00001209411,0.00005510129,0.0000154907,0.00001302913,0.002072706,0.8983718,0.01758007,0.08050831,0.0004300656,0.0002536547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001893929,0.00001539475,0.9919799,0.003453941,0.0008821951,0.0005424264,0.000171689,0.0001021176,0.0009584274],"genre_scores_gemma":[0.8687044,0.00005206034,0.1291533,0.001310957,0.0003754653,0.0001812634,0.00009276494,0.00002662439,0.000103164],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8668104,"threshold_uncertainty_score":0.9473428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1435383434496695,"score_gpt":0.3268560395712488,"score_spread":0.1833176961215794,"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."}}