{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002008645,0.0005475037,0.0006217618,0.0009216845,0.0005399078,0.0005448337,0.003007043,0.0003310298,0.00004701497],"category_scores_gemma":[0.0003905649,0.0005399277,0.00009875709,0.001584626,0.0002320412,0.0006342659,0.001212382,0.0003861545,0.00002163641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001466959,"about_ca_system_score_gemma":0.001404348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009694732,"about_ca_topic_score_gemma":0.00005922079,"domain_scores_codex":[0.9957714,0.00008794537,0.0004967694,0.001632704,0.0007325817,0.001278589],"domain_scores_gemma":[0.997564,0.0002955038,0.0003143924,0.001126729,0.0003818905,0.0003174618],"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":[0.00001976374,0.00007149357,0.00006798057,0.0001912294,0.00007274056,0.00006857594,0.004537521,0.8833039,0.0004216982,0.04532705,0.06358591,0.002332132],"study_design_scores_gemma":[0.0004516544,0.00004314778,0.000007038719,0.000673892,0.00001247567,0.00002105584,0.0005973681,0.9796669,0.0002737908,0.01355263,0.004075238,0.0006247857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002609584,0.0002953628,0.7821068,0.0003113131,0.0004568573,0.0005721476,0.000161035,0.001478279,0.2143572],"genre_scores_gemma":[0.5763538,0.000008612234,0.2514363,0.00212495,0.0002407135,0.0001367519,0.0002960388,0.0001151004,0.1692878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5760928,"threshold_uncertainty_score":0.9997053,"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."}}