{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002499392,0.0001115327,0.0001172663,0.0006367561,0.0005881605,0.004493637,0.0003014118,0.00009057839,0.00001988814],"category_scores_gemma":[0.0001601053,0.00009801434,0.00002820222,0.0009577987,0.000045771,0.01359476,0.0002317842,0.0002323774,0.0001376964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000168097,"about_ca_system_score_gemma":0.0004034903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006195657,"about_ca_topic_score_gemma":0.00001633071,"domain_scores_codex":[0.9979072,0.00009649602,0.0005338273,0.0001814292,0.0009039395,0.0003770644],"domain_scores_gemma":[0.9985897,0.000245915,0.00004891399,0.0002314427,0.0007730095,0.0001110503],"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":[0.00000153379,0.000006417495,0.00002284438,0.0001214431,0.000006400178,0.000002188458,0.005192921,0.55606,0.00004484938,0.4358914,0.0002998046,0.00235029],"study_design_scores_gemma":[0.00007550365,0.00003262548,0.000006184237,0.0001924754,0.000001210568,0.00003895881,0.001638424,0.9860438,0.0002917375,0.000626464,0.01093565,0.0001170022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007237496,0.0009231284,0.9830009,0.0002991893,0.0003336225,0.0006859427,0.00002175353,0.0001460028,0.007351914],"genre_scores_gemma":[0.9891824,0.0001198112,0.009936917,0.0001131686,0.0001307347,0.0001390805,0.00006377441,0.00000913505,0.0003049922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9819449,"threshold_uncertainty_score":0.9965398,"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."}}