{"id":"W6981969580","doi":"","title":"Game of thoughts: Iterative reasoning in game-theoretic domains with large language models","year":2025,"lang":"en","type":"other","venue":"Radboud Repository (Radboud University)","topic":"World Wars: History, Literature, and Impact","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada); University of Waterloo","funders":"","keywords":"Automated reasoning; Natural language; Domain (mathematical analysis); Language model; Feature (linguistics); Case-based reasoning; Set (abstract data type)","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":[0.005797193,0.0009635625,0.001030965,0.001438047,0.002169361,0.006958021,0.003044688,0.002503888,0.01764642],"category_scores_gemma":[0.03842022,0.0009571165,0.002422498,0.001560319,0.005254057,0.01148146,0.006181447,0.003199837,0.002395614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002302055,"about_ca_system_score_gemma":0.002744815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00915323,"about_ca_topic_score_gemma":0.01016493,"domain_scores_codex":[0.99504,0.003230038,0.0002420518,0.0005859166,0.000628764,0.0002731118],"domain_scores_gemma":[0.9722719,0.02459445,0.0004507495,0.001340811,0.0007261974,0.000615856],"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":[0.0002709201,0.0001397599,0.001080769,0.000383925,0.00009144116,0.0004870278,0.002237389,0.05393041,0.0007935039,0.8805074,0.01106506,0.04901245],"study_design_scores_gemma":[0.00006327673,0.00001840353,0.0001055293,0.00004495519,0.00002488056,0.00009470514,0.0004422802,0.2526215,0.0005389258,0.7390304,0.006992856,0.00002219644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01859351,0.0003425578,0.9501454,0.00216367,0.00008437737,0.0002707618,0.000502506,0.001450884,0.02644618],"genre_scores_gemma":[0.425328,0.0004641171,0.5598456,0.0003450218,0.0001133054,0.0005032179,0.001043763,0.0004993985,0.01185754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01764642,"threshold_uncertainty_score":0.05903322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00380023899883075,"score_gpt":0.2181446845262114,"score_spread":0.2143444455273806,"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."}}