{"id":"W4312237232","doi":"10.1145/3555858.3555880","title":"Charting the Uncharted with GUR: How AI Playtesting Can Supplement Expert Evaluation","year":2022,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science","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":[0.002004171,0.0001460402,0.0001077982,0.00008559749,0.001249889,0.0003702336,0.0009800766,0.00001448132,0.0006129362],"category_scores_gemma":[0.0001447812,0.0001004448,0.00003422469,0.0007837157,0.00004034502,0.0004312863,0.0005056466,0.000217833,0.00001546679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002658368,"about_ca_system_score_gemma":0.0002065727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007960269,"about_ca_topic_score_gemma":0.0005818989,"domain_scores_codex":[0.9974773,0.0003121679,0.0002224659,0.0004390636,0.001098228,0.0004507759],"domain_scores_gemma":[0.9987139,0.0001963083,0.0001360254,0.0006352297,0.0002497776,0.00006873475],"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":[0.00007161582,0.0005100233,0.006453135,0.00002614846,0.0001692018,0.0001249197,0.1010086,0.1405058,0.03714501,0.33185,0.06842855,0.3137071],"study_design_scores_gemma":[0.0001661824,0.0002509055,0.0001094195,0.000007420653,0.000007584949,0.00003016472,0.01016063,0.9416006,0.03569225,0.001579099,0.01017884,0.0002168988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1028974,0.0001450701,0.6765829,0.2138344,0.0006735947,0.001946327,0.000007801913,0.000610498,0.00330201],"genre_scores_gemma":[0.9881692,8.942442e-7,0.007029282,0.00380986,0.00008514483,0.0005034882,0.00001052381,0.00001265952,0.0003789639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8852718,"threshold_uncertainty_score":0.9613261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05651076799166636,"score_gpt":0.2969202972071227,"score_spread":0.2404095292154564,"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."}}