{"id":"W7124140261","doi":"10.65109/kzph7176","title":"Run the GAMUT: A Comprehensive Approach to Evaluating Game-Theoretic Algorithms","year":2004,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Benchmarking; Suite; Generator (circuit theory); Nash equilibrium; Test suite; Variation (astronomy)","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":[0.01265171,0.003137679,0.001833769,0.004268441,0.0007767891,0.003122785,0.003504526,0.001942389,0.003639078],"category_scores_gemma":[0.05854569,0.0008880499,0.001323268,0.002793376,0.002035221,0.004038066,0.00364264,0.00380666,0.0009380704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00145702,"about_ca_system_score_gemma":0.001844279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002392682,"about_ca_topic_score_gemma":0.004406882,"domain_scores_codex":[0.9898642,0.005968802,0.0005715957,0.0008738457,0.002317164,0.0004043722],"domain_scores_gemma":[0.9652825,0.0264854,0.001033928,0.004837141,0.001638582,0.0007224579],"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":[0.0009854488,0.001389539,0.01203073,0.001103614,0.0008550601,0.0002840188,0.0006109526,0.6351064,0.004620856,0.09139501,0.03224287,0.2193754],"study_design_scores_gemma":[0.0001324484,0.0003496339,0.0009415795,0.00006090572,0.00004091895,0.00009280293,0.00008121935,0.9299316,0.00373645,0.06007221,0.004514405,0.00004587209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07773283,0.0006648299,0.89556,0.0006152671,0.0001815037,0.0009453373,0.002202516,0.01313319,0.008964557],"genre_scores_gemma":[0.3288943,0.0003914434,0.6629792,0.0003513506,0.00006344025,0.001810697,0.002521287,0.001707923,0.001280356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01265171,"threshold_uncertainty_score":0.06690943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0996519275771312,"score_gpt":0.3512979275518514,"score_spread":0.2516459999747201,"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."}}