{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002365207,0.001129229,0.0006893083,0.0007279079,0.0004706802,0.001524016,0.002100689,0.001443754,0.01309655],"category_scores_gemma":[0.01059986,0.0005303141,0.001185882,0.0005840737,0.000855981,0.002451811,0.001708626,0.002115613,0.002549411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221946,"about_ca_system_score_gemma":0.001904982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00647822,"about_ca_topic_score_gemma":0.01114559,"domain_scores_codex":[0.9985447,0.000717478,0.00005856072,0.0002871561,0.0003018335,0.00009020039],"domain_scores_gemma":[0.9957574,0.003410222,0.0000881188,0.0004514633,0.0002131163,0.00007974153],"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":[0.0004602201,0.000300315,0.001998018,0.000568442,0.0001612083,0.0003814358,0.0004562858,0.4998176,0.005725246,0.07476289,0.02685899,0.3885094],"study_design_scores_gemma":[0.00005087981,0.00003788206,0.00006218599,0.00001648211,0.00001668413,0.00004410804,0.0000312475,0.9718992,0.001886956,0.02066161,0.005280985,0.00001183436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01076708,0.0005391404,0.9691548,0.0006582817,0.0001093817,0.0003071935,0.0008055993,0.01289214,0.004766379],"genre_scores_gemma":[0.2209253,0.0002555945,0.7699755,0.0006006415,0.00005939726,0.00045637,0.001903003,0.001268599,0.004555603],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01309655,"threshold_uncertainty_score":0.04381227,"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."}}