{"id":"W7124240789","doi":"10.65109/gzfu8152","title":"Game of Thoughts: Iterative Reasoning in Game-Theoretic Domains with Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada); University of Waterloo","funders":"","keywords":"Action (physics); Cognition; Hierarchy; Resource allocation; Resource (disambiguation); Game theory; Visual reasoning","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":[0.005125684,0.001162758,0.0009480552,0.0009600908,0.001150914,0.003854124,0.002958536,0.001588579,0.004918355],"category_scores_gemma":[0.02765943,0.0008746739,0.002411386,0.0007881742,0.004395082,0.006495112,0.003833769,0.003279345,0.0006230875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001715029,"about_ca_system_score_gemma":0.001968607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005540167,"about_ca_topic_score_gemma":0.006815854,"domain_scores_codex":[0.995723,0.002783141,0.0001645729,0.0006185503,0.0004767924,0.000233933],"domain_scores_gemma":[0.9779142,0.01892003,0.0008884266,0.001268832,0.0005014719,0.0005070036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001788188,0.0001961036,0.001903043,0.0002993535,0.0001520756,0.0004624283,0.002469521,0.3857426,0.002465052,0.5680907,0.001727953,0.03631229],"study_design_scores_gemma":[0.00003325537,0.00003146052,0.00008283969,0.00001964701,0.00002205174,0.00006073306,0.0001363889,0.6988468,0.0006063196,0.2986999,0.001439943,0.00002059429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02409358,0.0001222733,0.9708558,0.0005427913,0.00002600877,0.0001423641,0.00008738796,0.0003385396,0.003791161],"genre_scores_gemma":[0.4591747,0.0001834936,0.5375448,0.0002545346,0.00004226373,0.0003741628,0.0001981237,0.0001149792,0.00211297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005540167,"threshold_uncertainty_score":0.02710754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0195809553955015,"score_gpt":0.3480464282384963,"score_spread":0.3284654728429948,"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."}}