{"id":"W2201201022","doi":"10.1609/aiide.v8i1.12529","title":"The Gold Standard: Automatically Generating Puzzle Game Levels","year":2012,"lang":"en","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":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Genetic algorithm; Perspective (graphical); Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006467683,0.0003531186,0.0003179884,0.00009297,0.0003932824,0.001552793,0.001643224,0.00008015729,0.00003569447],"category_scores_gemma":[0.0009107565,0.0002149123,0.0001780501,0.0003126219,0.0006412838,0.002265342,0.0008791044,0.0003837421,0.00008858083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509877,"about_ca_system_score_gemma":0.00005703343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001254909,"about_ca_topic_score_gemma":0.000006324642,"domain_scores_codex":[0.9972066,0.00003428233,0.0008571316,0.0004733503,0.0007407311,0.0006878779],"domain_scores_gemma":[0.9979392,0.0004221859,0.0005050972,0.0003736035,0.0005594966,0.0002004411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009376526,0.0002166956,0.0004681675,0.00001757733,0.00005811605,4.241502e-7,0.004657364,0.00002476903,0.009152818,0.6833792,0.0001877371,0.3017434],"study_design_scores_gemma":[0.00005695197,0.0007915478,0.0005299501,0.0005234202,0.00002808752,0.00002816621,0.009878317,0.1042196,0.7698658,0.1094824,0.003950079,0.000645738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7443032,0.000261965,0.1864905,0.01480539,0.002746634,0.001962219,0.00006353941,0.0002872148,0.04907933],"genre_scores_gemma":[0.9979533,0.00004120683,0.0009106825,0.0003204103,0.0001262371,0.00006027453,5.999344e-7,0.00001831386,0.0005689723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7607129,"threshold_uncertainty_score":0.9994837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05441993521379222,"score_gpt":0.3023131973587647,"score_spread":0.2478932621449725,"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."}}