{"id":"W6929156192","doi":"10.48448/xzx6-9a93","title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Advanced Photonic Communication Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Benchmark (surveying); Decision model; Decision support system; Task (project management); Plan (archaeology); Decision analysis; Code (set theory); Decision theory; Generative model","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005907509,0.0003542036,0.0003348558,0.0006294881,0.0001424276,0.0001794614,0.0007009438,0.0002256036,0.000224511],"category_scores_gemma":[0.00007830402,0.0003296002,0.00007758106,0.000626028,0.0001323955,0.000209136,0.0001572302,0.0002918439,0.0002875773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004052301,"about_ca_system_score_gemma":0.0002073512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004172002,"about_ca_topic_score_gemma":0.0003599788,"domain_scores_codex":[0.9979452,0.00002843294,0.000404273,0.0005810403,0.0005893453,0.0004517397],"domain_scores_gemma":[0.9986927,0.0000953916,0.0001178135,0.0008710853,0.00008882287,0.0001342066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001033533,0.0001505421,0.000001565434,0.0005062094,0.0004159553,0.00004178462,0.008064994,0.1960994,0.09636849,0.03799295,0.648195,0.01205968],"study_design_scores_gemma":[0.0004897022,0.00004068083,8.624677e-8,0.0002097599,0.00002629678,0.00001320745,0.0004884909,0.8271013,0.003024862,0.001379129,0.1668783,0.0003481085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000762503,0.008266826,0.8815529,0.00007727198,0.002520696,0.001830063,0.00119587,0.001343131,0.1024507],"genre_scores_gemma":[0.2497957,0.001469717,0.2483684,0.0007131802,0.003233951,0.0007489405,0.003603338,0.002879285,0.4891875],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6331846,"threshold_uncertainty_score":0.9999156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03670480921906746,"score_gpt":0.3240012621525827,"score_spread":0.2872964529335152,"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."}}