{"id":"W3211267996","doi":"10.1145/3459637.3482397","title":"The Skyline of Counterfactual Explanations for Machine Learning Decision Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Nanyang Technological University; National Research Foundation Singapore; National Research Foundation","keywords":"Counterfactual thinking; Skyline; Computer science; Machine learning; Measure (data warehouse); Artificial intelligence; Function (biology); Frame (networking); Minification; Data mining; Mathematical optimization; Mathematics","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":[0.0004566837,0.00007348001,0.000101288,0.00004185511,0.0003269114,0.0001317434,0.000523466,0.00003055498,0.00003127318],"category_scores_gemma":[0.0004802942,0.00005164692,0.0000603215,0.0002771711,0.00003290235,0.0004175098,0.0001770293,0.00008282563,0.00001596516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002307397,"about_ca_system_score_gemma":0.00008873909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005497749,"about_ca_topic_score_gemma":0.0004212704,"domain_scores_codex":[0.9990354,0.00004136775,0.0002816164,0.0002144094,0.0002357442,0.0001914957],"domain_scores_gemma":[0.997674,0.001406702,0.00007185394,0.0003664535,0.0004413531,0.00003956221],"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":[0.00001679291,0.00005755785,0.00003347261,0.000005297547,0.00001552989,0.000003259262,0.0008441925,0.08266359,0.00191479,0.826361,0.0008691513,0.08721536],"study_design_scores_gemma":[0.00006816922,0.00004983464,0.000006730174,0.000008259407,0.000002433429,0.000004489973,0.0003655138,0.8529529,0.06458892,0.06851693,0.01337558,0.00006021627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004720883,0.0003105479,0.990916,0.001350858,0.0001831004,0.0001110695,0.00000419359,0.00005371397,0.00234959],"genre_scores_gemma":[0.8998035,0.0001352927,0.09684451,0.0001318328,0.00002829456,0.00002067953,0.000007030805,0.000007592258,0.003021287],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8950826,"threshold_uncertainty_score":0.2514371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04505692472593091,"score_gpt":0.293800081891528,"score_spread":0.2487431571655971,"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."}}