{"id":"W7082283797","doi":"10.48448/31bp-2525","title":"LLMs as Planning Modelers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Software deployment; Construct (python library); Natural language; Plan (archaeology); Language planning; Natural (archaeology); Decision support system; Modeling language","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":[0.005192232,0.001905306,0.00104543,0.004252684,0.0006851782,0.006221926,0.003195914,0.001497616,0.006075685],"category_scores_gemma":[0.01634773,0.001342649,0.001817575,0.004874132,0.002260969,0.008047172,0.003482,0.00351106,0.002600289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002592301,"about_ca_system_score_gemma":0.004200141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009621013,"about_ca_topic_score_gemma":0.01058574,"domain_scores_codex":[0.9966412,0.001638889,0.0003052564,0.0004572501,0.0008293916,0.000128045],"domain_scores_gemma":[0.9876025,0.009131054,0.0005327307,0.001616362,0.0009026576,0.0002146314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007369048,0.0001126359,0.00209109,0.002727629,0.0001868419,0.0002166202,0.001249803,0.09833766,0.001476388,0.3504184,0.01389276,0.5292165],"study_design_scores_gemma":[0.00002290325,0.00006601809,0.0005878704,0.002056817,0.0001278597,0.0002645455,0.0006975404,0.3603222,0.003207119,0.3604751,0.2720626,0.0001094507],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.002891594,0.02564139,0.9510975,0.003181041,0.0001403771,0.0001355112,0.0006264442,0.003215104,0.01307097],"genre_scores_gemma":[0.07868199,0.05486734,0.8575894,0.0009216666,0.0002820352,0.0004920233,0.001911242,0.001204262,0.004049953],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009621013,"threshold_uncertainty_score":0.0274595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05932792165085742,"score_gpt":0.3252093958823399,"score_spread":0.2658814742314825,"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."}}