{"id":"W4416013988","doi":"10.1609/aiide.v21i1.36846","title":"FighterDDA: A Simulation Testbed for Evaluating Director-Based Dynamic Balancing","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"University of California, Santa Cruz; National Science Foundation","keywords":"Testbed; Key (lock); Visualization","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008266353,0.0007525575,0.0007774574,0.0004776473,0.0005955035,0.002011027,0.001758791,0.0002196535,0.00005649333],"category_scores_gemma":[0.003281686,0.0006200342,0.0004841565,0.0008671183,0.0006575672,0.001798827,0.0008042532,0.0005430105,0.00002960572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005444927,"about_ca_system_score_gemma":0.0003717953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003523281,"about_ca_topic_score_gemma":0.00001482888,"domain_scores_codex":[0.9950886,0.0000590232,0.001802492,0.00142581,0.0008419923,0.0007820624],"domain_scores_gemma":[0.9941021,0.001784872,0.001259966,0.0004987746,0.002188147,0.0001661695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001785491,0.001280448,0.000948915,0.0005015219,0.0002710899,9.152523e-7,0.004087291,0.008986161,0.02705791,0.1333436,0.00006905432,0.8216676],"study_design_scores_gemma":[0.00009537787,0.001136615,0.0001614818,0.002904276,0.00007816563,9.800655e-7,0.002278811,0.7297922,0.2146031,0.04841529,0.0001304452,0.0004032911],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3388417,0.0001855114,0.6395219,0.006734066,0.002586639,0.004256717,0.0001534201,0.0001319258,0.007588071],"genre_scores_gemma":[0.9970687,0.00002708401,0.001093178,0.0006200839,0.00006160317,0.0002335442,0.00000676408,0.00003509585,0.0008539155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8212643,"threshold_uncertainty_score":0.9996251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06346907629870756,"score_gpt":0.3631617434673035,"score_spread":0.2996926671685959,"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."}}