{"id":"W4401571420","doi":"10.1080/03155986.2024.2385189","title":"Diagnosing infeasible optimization problems using large language models","year":2024,"lang":"en","type":"article","venue":"INFOR Information Systems and Operational Research","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Solver; Optimization problem; Artificial intelligence; Natural language; Machine learning; Mathematical optimization; Programming language; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.004932293,0.002008802,0.0009940374,0.001309663,0.001314415,0.002865246,0.002545322,0.001831245,0.009675867],"category_scores_gemma":[0.03698912,0.0008874806,0.001990811,0.0005608703,0.001616978,0.004313615,0.003422151,0.003445802,0.00144422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001987181,"about_ca_system_score_gemma":0.003148168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007153707,"about_ca_topic_score_gemma":0.01999071,"domain_scores_codex":[0.9956255,0.00244027,0.0002377198,0.000788973,0.000746791,0.0001607587],"domain_scores_gemma":[0.9593554,0.03648661,0.001192132,0.001236347,0.001336376,0.0003932416],"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":[0.0009071958,0.0007698903,0.006122173,0.001595884,0.0002341277,0.002067187,0.003125877,0.6977574,0.01050819,0.06577059,0.02044741,0.1906941],"study_design_scores_gemma":[0.00005659434,0.00004315204,0.0001777604,0.00005408356,0.00001736978,0.00006963439,0.0002092032,0.9556578,0.001915995,0.03822733,0.003548065,0.00002294121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04167622,0.0002350821,0.9433885,0.001691113,0.00007423307,0.0003773445,0.0009692807,0.00795063,0.003637544],"genre_scores_gemma":[0.314876,0.0001887959,0.6785267,0.0007167414,0.00005957298,0.0005592789,0.002219027,0.0007415767,0.002112288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009675867,"threshold_uncertainty_score":0.03236896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1203811663468925,"score_gpt":0.3876422347020393,"score_spread":0.2672610683551468,"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."}}