{"id":"W1680175220","doi":"10.1109/cgames.2015.7272961","title":"Exploring options for efficiently evaluating the playability of computer game agents","year":2015,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Human–computer interaction; Game theory; Computer game; Multimedia","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":[],"consensus_categories":[],"category_scores_codex":[0.001648949,0.00008882093,0.0001219147,0.00004599801,0.00009438738,0.0000815852,0.0008926427,0.00002140707,0.0000093633],"category_scores_gemma":[0.0003550243,0.00006006988,0.00008067682,0.000256251,0.00009840245,0.0004094529,0.0003197587,0.00006390366,0.00003644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004686155,"about_ca_system_score_gemma":0.00008116611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005063394,"about_ca_topic_score_gemma":0.00001057288,"domain_scores_codex":[0.9987078,0.000100561,0.0003375823,0.0002722336,0.0003636895,0.0002180777],"domain_scores_gemma":[0.9983143,0.0005520451,0.00009977283,0.00059444,0.00036547,0.00007396756],"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":[0.00004271241,0.0003881308,0.002123039,0.0000373584,0.00004707506,9.63606e-7,0.02556163,0.3738722,0.001211289,0.2192711,0.002003417,0.375441],"study_design_scores_gemma":[0.00007793125,0.0002618121,0.0008747947,0.00001142715,0.000004968036,0.000001344912,0.0003554077,0.9826987,0.008560639,0.006625338,0.0004460663,0.00008158747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3617641,0.00001248318,0.6366155,0.0004389807,0.0005613926,0.0002789164,0.000001091829,0.00005789376,0.0002696517],"genre_scores_gemma":[0.8437963,0.0000012099,0.1558358,0.0001109311,0.00008892094,0.00007910439,5.837329e-7,0.000004893314,0.00008225052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6088265,"threshold_uncertainty_score":0.2449578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5630705450574971,"score_gpt":0.4239186773164916,"score_spread":0.1391518677410055,"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."}}