{"id":"W4416034391","doi":"10.18653/v1/2025.findings-emnlp.1386","title":"STA-CoT: Structured Target-Centric Agentic Chain-of-Thought for Consistent Multi-Image Geological Reasoning","year":2025,"lang":"","type":"article","venue":"","topic":"Geological Modeling and Analysis","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Argument (complex analysis); Context (archaeology); Interpretation (philosophy); Perspective (graphical); Reflection (computer programming)","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":[0.003779368,0.001966068,0.00109652,0.001155357,0.001391735,0.002905494,0.005289647,0.002159646,0.005482757],"category_scores_gemma":[0.01500639,0.001079611,0.002376851,0.0007619478,0.002633087,0.003759182,0.006652835,0.003498381,0.001684344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00174982,"about_ca_system_score_gemma":0.006345626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01977136,"about_ca_topic_score_gemma":0.0447771,"domain_scores_codex":[0.9964547,0.000914218,0.0003013049,0.0007872624,0.001220485,0.0003218816],"domain_scores_gemma":[0.9923491,0.002805294,0.000642442,0.002289728,0.001479354,0.0004340615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008038532,0.0005259432,0.006505382,0.001031904,0.0004410376,0.001041772,0.001645764,0.6161714,0.02761051,0.08409875,0.02425387,0.2358699],"study_design_scores_gemma":[0.00005305326,0.00005163396,0.0001274349,0.0000269208,0.00004083896,0.00006287859,0.00009183915,0.9618486,0.005239593,0.02561534,0.006817522,0.00002438946],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00729405,0.0001413578,0.9769967,0.0002543948,0.00007324194,0.0002523169,0.0003016786,0.01226544,0.002420808],"genre_scores_gemma":[0.1776652,0.0001198292,0.8161806,0.0003156254,0.00003525089,0.0003101124,0.001490113,0.001403847,0.002479498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01977136,"threshold_uncertainty_score":0.03931254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02661213531258422,"score_gpt":0.2552277005097201,"score_spread":0.2286155651971359,"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."}}