{"id":"W4318145939","doi":"10.48550/arxiv.2301.10074","title":"Explainable Data-Driven Optimization: From Context to Decision and Back Again","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Interpretability; Counterfactual thinking; Computer science; Random forest; Bridge (graph theory); Machine learning; Context (archaeology); Decision tree; Artificial intelligence; Key (lock); Data science; Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005441631,0.001528306,0.001449213,0.001606224,0.0009029606,0.00344435,0.002509666,0.002525309,0.005625726],"category_scores_gemma":[0.03097739,0.0009248159,0.001759057,0.001428412,0.004233229,0.005223698,0.003607229,0.005200647,0.0003854695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002872774,"about_ca_system_score_gemma":0.002479738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005489931,"about_ca_topic_score_gemma":0.005330951,"domain_scores_codex":[0.9955078,0.002854963,0.0001882527,0.0006845059,0.0005136796,0.0002507278],"domain_scores_gemma":[0.9781138,0.01717783,0.001546655,0.00187646,0.0009194228,0.0003658624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001056999,0.0001022508,0.002732314,0.0003127783,0.0001976992,0.0003895451,0.0005964802,0.2662931,0.0003909287,0.6888269,0.003280396,0.03677195],"study_design_scores_gemma":[0.00002320321,0.00001967864,0.0002971394,0.00007237851,0.0000256084,0.00002998249,0.00006962991,0.3218227,0.0002133609,0.6751596,0.00224187,0.00002482234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0152012,0.001016541,0.9727466,0.006112994,0.0001490844,0.00006156662,0.0002968329,0.0002119978,0.004203068],"genre_scores_gemma":[0.6733042,0.001368317,0.3200677,0.001003568,0.0003844159,0.000322393,0.0005834354,0.0002256574,0.002740361],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005625726,"threshold_uncertainty_score":0.02877849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2032097652387366,"score_gpt":0.2395985744327592,"score_spread":0.03638880919402254,"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."}}