{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003284053,0.0004875466,0.0007925662,0.001449912,0.0003319058,0.0001508758,0.0007269979,0.0005908795,0.00009653952],"category_scores_gemma":[0.00004242013,0.0004804356,0.0002032809,0.001384661,0.0008451545,0.0003714992,0.00009487539,0.000650841,0.000004962104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001039283,"about_ca_system_score_gemma":0.00119325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004131819,"about_ca_topic_score_gemma":0.002041182,"domain_scores_codex":[0.9967281,0.0009305224,0.0003243896,0.0007160708,0.0006110042,0.0006899321],"domain_scores_gemma":[0.9983027,0.0001480077,0.0005336162,0.0006449195,0.0001386052,0.0002321443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004858349,0.0005813312,0.001238099,0.0004030661,0.0005332558,0.002774142,0.1414429,0.0007573196,0.00008721845,0.8094664,0.04209846,0.0001320339],"study_design_scores_gemma":[0.001948734,0.0001848222,0.00009867352,0.002939798,0.000269237,0.00001129948,0.01817924,0.0003137403,0.00006360139,0.0003207166,0.9748024,0.000867726],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00388409,0.005442544,0.001508278,0.00003214767,0.001027014,0.0007190775,0.0001941682,0.0002396155,0.9869531],"genre_scores_gemma":[0.1777215,0.0005072144,0.0003688095,0.0000320646,0.000565703,0.000002709935,0.00004518643,0.0001429366,0.8206139],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.932704,"threshold_uncertainty_score":0.9997647,"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."}}