{"id":"W4414031611","doi":"10.1613/jair.1.18144","title":"Optimal Decision Trees for Interpretable and Constrained Clustering","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Toronto; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Cluster analysis; Computer science; Artificial intelligence; Decision tree; Machine learning; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002498397,0.0000659358,0.0001550845,0.0003994027,0.0002425218,0.0004603168,0.0007864407,0.00004342182,0.000007970101],"category_scores_gemma":[0.000911097,0.00005486376,0.00005458716,0.0005499203,0.0001629058,0.0003977637,0.0003224894,0.0002509863,0.000004611983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000419924,"about_ca_system_score_gemma":0.000212575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001400608,"about_ca_topic_score_gemma":0.00002041994,"domain_scores_codex":[0.9987627,0.00005050936,0.0004557834,0.0001890943,0.0002879736,0.000253889],"domain_scores_gemma":[0.9975955,0.001409855,0.00008519874,0.0002249007,0.0005931821,0.00009131108],"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":[0.0000529913,0.00005298196,0.000009149874,0.00001046222,0.00001484736,0.000004029665,0.0003279398,0.0007676241,0.003281912,0.04425559,0.00061255,0.9506099],"study_design_scores_gemma":[0.00005134961,0.0003085383,0.00004185872,0.0001962257,0.000004899438,0.00003112603,0.0009745793,0.9211384,0.01496937,0.0588286,0.003388449,0.00006658491],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01550288,0.000183941,0.9821101,0.001590466,0.0001976452,0.0001434814,0.000004415941,0.000009129503,0.0002579551],"genre_scores_gemma":[0.4604657,0.0001106953,0.5391833,0.00002987449,0.00008412239,0.00001142487,3.342586e-7,0.00000370521,0.0001109138],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9505433,"threshold_uncertainty_score":0.4438846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1133541147254846,"score_gpt":0.4426594675277677,"score_spread":0.3293053528022831,"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."}}