{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009364225,0.001069832,0.0009960989,0.001524763,0.0008291451,0.003824722,0.001943463,0.00167528,0.002192683],"category_scores_gemma":[0.06638033,0.0009471271,0.001336468,0.0006658346,0.003348715,0.007674193,0.003248464,0.002799832,0.0002236423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002230451,"about_ca_system_score_gemma":0.001996632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001993098,"about_ca_topic_score_gemma":0.0026835,"domain_scores_codex":[0.9918661,0.004620492,0.0004035465,0.0009483491,0.001568231,0.0005933565],"domain_scores_gemma":[0.9219545,0.07043582,0.002978899,0.00277209,0.00123344,0.0006251459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005565574,0.0003345305,0.008690473,0.0003059529,0.000130929,0.0001724221,0.0005415619,0.6963454,0.005515791,0.2181494,0.0009082206,0.06834885],"study_design_scores_gemma":[0.00003855018,0.0001022199,0.000493128,0.00002203846,0.00002381969,0.0000350076,0.0001047319,0.8636763,0.002094437,0.1328842,0.0005061408,0.00001947251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2624677,0.000308637,0.7290012,0.001267847,0.00002507043,0.0002292074,0.000128499,0.0003159154,0.006255937],"genre_scores_gemma":[0.8207476,0.0001689725,0.1778223,0.00008351651,0.0000247942,0.0002053461,0.0001701264,0.00009968563,0.0006777181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009364225,"threshold_uncertainty_score":0.04952341,"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."}}