{"id":"W4365452225","doi":"10.1016/j.patcog.2023.109610","title":"Learning Customised Decision Trees for Domain-knowledge Constraints","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Fonds De La Recherche Scientifique - FNRS","keywords":"Computer science; Machine learning; Decision tree; Binary decision diagram; Domain (mathematical analysis); Incremental decision tree; Artificial intelligence; Tree (set theory); Representation (politics); Domain knowledge; Discretization; Decision tree learning; Theoretical computer science; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007323617,0.0001540313,0.0001622277,0.0002847251,0.0003032296,0.0001919733,0.0004131424,0.00008998954,0.0001021643],"category_scores_gemma":[0.0003099531,0.0001586617,0.000110094,0.0005806359,0.00006512223,0.0004364133,0.0001314917,0.0001350759,0.004119652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000614251,"about_ca_system_score_gemma":0.00004589147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009760718,"about_ca_topic_score_gemma":0.00007174646,"domain_scores_codex":[0.9984911,0.0001019458,0.0003120905,0.000467253,0.0001957935,0.0004317896],"domain_scores_gemma":[0.9985058,0.0008122994,0.0001060717,0.0002458603,0.0002276211,0.0001023476],"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":[0.00001406353,0.00003877658,0.0003502817,0.00001987695,0.000009311652,0.00001287336,0.001388559,0.00007393962,0.0037982,0.000320214,0.0009680425,0.9930059],"study_design_scores_gemma":[0.00290167,0.00115226,0.008434589,0.0008400344,0.00004672147,0.00006884,0.00399666,0.5572448,0.1395592,0.253265,0.03071782,0.001772345],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2654022,0.00001314889,0.7313461,0.0003022173,0.0005357581,0.0003921608,0.00001040826,0.0004792119,0.001518778],"genre_scores_gemma":[0.9888033,0.00002543302,0.01034163,0.0001301643,0.0001674474,0.0002104078,0.00007155682,0.00002289375,0.0002271175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9912335,"threshold_uncertainty_score":0.9966558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0616607895682781,"score_gpt":0.3154847604653664,"score_spread":0.2538239708970884,"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."}}