{"id":"W4401386467","doi":"10.1080/03155986.2024.2381306","title":"Optimization modeling and verification from problem specifications using a multi-agent multi-stage LLM framework","year":2024,"lang":"en","type":"article","venue":"INFOR Information Systems and Operational Research","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Task (project management); Modeling language; Solver; Representation (politics); Artificial intelligence; Optimization problem; Machine learning; Programming language; Systems engineering; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001174422,0.0001656345,0.000172307,0.0007934952,0.0008041668,0.004553191,0.000136852,0.0001460798,0.00004905452],"category_scores_gemma":[0.0002381992,0.0001471874,0.00003687381,0.0008779712,0.00006462246,0.006394363,0.0001130352,0.0002838039,0.000106503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008380702,"about_ca_system_score_gemma":0.0001309567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003035655,"about_ca_topic_score_gemma":0.00002337891,"domain_scores_codex":[0.9981662,0.0000236545,0.0006630093,0.000268923,0.0006415523,0.0002366824],"domain_scores_gemma":[0.9982607,0.00008595095,0.0001117414,0.0001849726,0.001320805,0.00003586649],"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":[0.00001260163,0.0000275051,0.0004395114,0.0004927806,0.00003752378,5.56313e-7,0.0007211714,0.9422927,0.00007882585,0.05348779,0.00005562,0.002353453],"study_design_scores_gemma":[0.0002267845,0.000003449396,0.0001380872,0.0003268497,0.00002231001,0.000001674628,0.001855102,0.9863672,0.00000362723,0.0001682838,0.01071471,0.0001719018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03266638,0.0009797479,0.9644551,0.0004957877,0.0001918992,0.0005459893,0.00005379963,0.0001202905,0.0004909803],"genre_scores_gemma":[0.96466,0.0002434628,0.03340749,0.0001484794,0.000486075,0.0001450413,0.0006893779,0.00002007167,0.0001999739],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9319937,"threshold_uncertainty_score":0.9964802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2535615152377986,"score_gpt":0.3732107720741901,"score_spread":0.1196492568363914,"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."}}