{"id":"W4398220220","doi":"10.1007/978-3-031-60924-4_24","title":"Optimal Counterfactual Explanations for k-Nearest Neighbors Using Mathematical Optimization and Constraint Programming","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; University of Waterloo; Concordia University","funders":"","keywords":"Counterfactual thinking; Computer science; Constraint programming; Constraint (computer-aided design); Mathematical optimization; k-nearest neighbors algorithm; Algorithm; Artificial intelligence; Stochastic programming; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005616757,0.0003801176,0.0003594126,0.0004699161,0.0002580213,0.001369845,0.0008958024,0.0002499153,0.00001150074],"category_scores_gemma":[0.00006517664,0.0003480119,0.00007569158,0.000272316,0.0006355564,0.0004841814,0.0004957582,0.0004481242,0.000005776422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001720389,"about_ca_system_score_gemma":0.0004488425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005524508,"about_ca_topic_score_gemma":0.000006690834,"domain_scores_codex":[0.9975234,0.00001188604,0.0004414649,0.00107127,0.0004839532,0.0004680076],"domain_scores_gemma":[0.9986473,0.0003595691,0.0001391967,0.0004510387,0.000249993,0.0001528887],"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":[0.000002692872,0.00001680014,0.000001114281,0.0001058809,0.00001351636,0.00001940998,0.0009894005,0.7081769,0.00002776955,0.1591498,0.000003291528,0.1314935],"study_design_scores_gemma":[0.0001117794,0.0001025072,3.157707e-7,0.0005268301,0.00001763297,0.0001267785,0.000001219733,0.9160306,0.00009179428,0.08250884,0.0001268151,0.0003548977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007580603,0.0002306978,0.9976718,0.0004828417,0.0005574488,0.0004928216,0.00001713602,0.0001638821,0.0003075248],"genre_scores_gemma":[0.06526845,0.0000145297,0.9342606,0.0001641291,0.00016319,0.00001657579,0.000007638911,0.00002862927,0.00007627579],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2078537,"threshold_uncertainty_score":0.9998972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03851216212261793,"score_gpt":0.2848608348532083,"score_spread":0.2463486727305904,"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."}}