{"id":"W2156523042","doi":"10.1109/aamas.2004.238","title":"Run the GAMUT: A Comprehensive Approach to Evaluating Game-Theoretic Algorithms","year":2004,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Gamut; Computer science; Suite; Benchmarking; Generator (circuit theory); Test suite; Nash equilibrium; Theoretical computer science; Variation (astronomy); Architecture; Algorithm; Artificial intelligence; Machine learning; Mathematical optimization; Test case; Mathematics","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":[0.0005291637,0.000195849,0.0001811822,0.00008488908,0.0002205945,0.0003078731,0.001781838,0.00005422117,0.00002934988],"category_scores_gemma":[0.0001673643,0.0001276611,0.00009115877,0.0006987433,0.0001898051,0.0002469373,0.0005493676,0.0001998777,0.0007612644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008921513,"about_ca_system_score_gemma":0.000109963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001449108,"about_ca_topic_score_gemma":0.000009941457,"domain_scores_codex":[0.9979529,0.000123235,0.0003320806,0.0005484761,0.0005857062,0.0004576051],"domain_scores_gemma":[0.9983668,0.0002181688,0.00007397876,0.0009523162,0.0002479656,0.0001408204],"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":[0.000005068857,0.0001059623,0.00001857365,0.000007602385,0.0000178632,0.000004351509,0.01120317,0.06115428,0.001004067,0.831224,0.0002336872,0.09502133],"study_design_scores_gemma":[0.0001779532,0.0003176272,0.0003019993,0.00003912918,0.00001425439,0.00006404462,0.002872914,0.7056271,0.02068695,0.2675635,0.001858913,0.000475628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02538821,0.00008796492,0.9534734,0.002675639,0.0003098803,0.0005510901,6.080671e-7,0.000262167,0.01725098],"genre_scores_gemma":[0.6596028,0.000004224974,0.3371922,0.002660794,0.0001090349,0.00007083466,5.803017e-7,0.00001359541,0.0003459338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6444728,"threshold_uncertainty_score":0.9784768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08309830794725798,"score_gpt":0.3423465536720401,"score_spread":0.2592482457247821,"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."}}