{"id":"W2970130737","doi":"10.48550/arxiv.1909.02128","title":"No Press Diplomacy: Modeling Multi-Agent Gameplay","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Diplomacy; Reinforcement learning; Computer science; Teamwork; Benchmark (surveying); Artificial intelligence; Multi-agent system; Artificial neural network; Political science; Law","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":[],"consensus_categories":[],"category_scores_codex":[0.00005681122,0.0001272265,0.0001418267,0.00003075095,0.00009996883,0.00003573893,0.00024397,0.00004231545,0.0002777207],"category_scores_gemma":[0.000001956716,0.000143299,0.0001154045,0.0001125428,0.00002854866,0.0002139743,0.0001109028,0.0001358603,0.0005802199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000362836,"about_ca_system_score_gemma":0.00003130435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005102172,"about_ca_topic_score_gemma":0.000003523084,"domain_scores_codex":[0.9992697,0.00002842175,0.0001021847,0.0003273951,0.00004262143,0.0002296536],"domain_scores_gemma":[0.999455,0.00002131719,0.0000610786,0.0002763003,0.00009129511,0.0000949653],"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":[0.00002121213,0.0001333679,0.08114075,0.00001212086,0.00007293007,0.000005765738,0.0001626314,0.5586275,0.0001884878,0.3594336,0.00004998027,0.0001517324],"study_design_scores_gemma":[0.0005877829,0.00001905171,0.0005221441,0.00001555688,0.00001573917,6.703625e-8,0.0001588595,0.9939219,0.00002307314,0.002849853,0.001681186,0.0002047485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9017261,0.000009668734,0.07377129,0.000005930888,0.0002498246,0.0001649719,0.00002439142,0.0000428446,0.02400503],"genre_scores_gemma":[0.9903744,0.00001148236,0.000130801,0.00002959714,0.00007808198,4.731185e-7,0.00001244622,0.0000138367,0.009348894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4352945,"threshold_uncertainty_score":0.7457747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05642456405587556,"score_gpt":0.2053329976250018,"score_spread":0.1489084335691262,"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."}}