{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008912983,0.0007661895,0.000488693,0.0006580944,0.0004651237,0.001030728,0.001696027,0.0007875556,0.005943768],"category_scores_gemma":[0.004013683,0.0005427382,0.0005547762,0.0002654392,0.0009503098,0.001785285,0.00226199,0.0009908275,0.001562628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006779769,"about_ca_system_score_gemma":0.001141246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002172262,"about_ca_topic_score_gemma":0.003493488,"domain_scores_codex":[0.9993062,0.0001708471,0.00004889859,0.0001476954,0.0002611567,0.00006528065],"domain_scores_gemma":[0.9991918,0.0003022937,0.00004701078,0.0002304779,0.0001666051,0.00006176093],"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":[0.0007236405,0.0004494839,0.004826599,0.0004609413,0.0001483091,0.0005726278,0.001003832,0.1567643,0.05971536,0.1129376,0.02540793,0.6369894],"study_design_scores_gemma":[0.0001575884,0.0003137922,0.0007026225,0.00007438507,0.0000416827,0.0002374072,0.0001416831,0.8829262,0.04026421,0.04432938,0.03075678,0.00005426105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04754154,0.0001473057,0.9186369,0.0002292389,0.0001024024,0.0003123806,0.0002402619,0.01907521,0.01371477],"genre_scores_gemma":[0.2966835,0.0001137632,0.6894247,0.0002383543,0.00001201374,0.0002118035,0.0009462206,0.002648658,0.00972098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005943768,"threshold_uncertainty_score":0.01988393,"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."}}