{"id":"W2796683355","doi":"10.1145/3183568","title":"Usertesting Without the User","year":2018,"lang":"en","type":"article","venue":"Computers in entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"University of Ontario Institute of Technology","keywords":"Computer science; Proxy (statistics); Process (computing); Human–computer interaction; Population; Human intelligence; Artificial intelligence; Cognition; Data science; Machine learning; Psychology","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":[0.0004289894,0.0001533995,0.0001330442,0.00008547977,0.0001650587,0.0002053272,0.001730285,0.00003503537,0.00001486523],"category_scores_gemma":[0.00005060771,0.000109611,0.00004957462,0.0003170602,0.0002000559,0.0002555015,0.0006873498,0.0001466773,0.0001729459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001154461,"about_ca_system_score_gemma":0.00002834895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000066919,"about_ca_topic_score_gemma":0.00007330908,"domain_scores_codex":[0.9985016,0.0001098071,0.0003152372,0.0003969025,0.0002909895,0.0003854433],"domain_scores_gemma":[0.9988325,0.000218943,0.00008377245,0.0007475943,0.00005560448,0.00006157879],"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":[0.00003771316,0.000498301,0.2991714,0.00002312135,0.00007969026,0.0001097624,0.03452543,0.002382684,0.001462878,0.1534563,0.01085497,0.4973978],"study_design_scores_gemma":[0.0002992421,0.0003459901,0.01966382,0.0002266788,0.000005918247,0.00004468466,0.0004628536,0.9298341,0.01025859,0.01428031,0.02408855,0.0004893182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1466116,0.00003410488,0.8474718,0.002167501,0.001575263,0.0002392206,1.844628e-7,0.0001327216,0.001767548],"genre_scores_gemma":[0.9394867,0.000004021229,0.05803281,0.002135108,0.0002085546,0.00002144883,2.975205e-7,0.000009504157,0.0001015598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9274514,"threshold_uncertainty_score":0.4469808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02711012667811259,"score_gpt":0.2887080969848481,"score_spread":0.2615979703067355,"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."}}