{"id":"W2171494278","doi":"","title":"Software testing by active learning for commercial games","year":2005,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Alberta","funders":"","keywords":"Computer science; Correctness; Video game; Context (archaeology); Software engineering; Software performance testing; Artificial intelligence; White-box testing; Software; Active learning (machine learning); Machine learning; Human–computer interaction; Software construction; Software system; Multimedia; Programming language","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":[0.0005492026,0.0001975351,0.0001775171,0.0001561435,0.0004196099,0.0002746581,0.0007443546,0.0001048541,0.000038535],"category_scores_gemma":[0.00638142,0.0002044574,0.00007922899,0.0003884084,0.00009354356,0.0003947336,0.0001062781,0.0003285767,0.0000902721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001396919,"about_ca_system_score_gemma":0.0002497496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003012149,"about_ca_topic_score_gemma":0.00001151094,"domain_scores_codex":[0.9981986,0.00007444854,0.0003519996,0.0005054307,0.0005392061,0.0003302945],"domain_scores_gemma":[0.9962119,0.002224769,0.0001820749,0.000192988,0.001096351,0.00009185479],"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":[0.00002027314,0.00009055308,0.0001461742,0.000004307231,0.000006952087,3.965962e-7,0.0002069431,0.001208571,0.0003215058,0.1177773,0.004473443,0.8757436],"study_design_scores_gemma":[0.00004746905,0.0003573811,0.0004891561,0.00009350755,0.000005122787,0.000004809984,0.00002556935,0.5101072,0.03686424,0.4477446,0.003842157,0.0004187551],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001462937,0.00002045603,0.9905042,0.001944,0.0001419034,0.0002421065,0.00001742238,0.003142001,0.002524942],"genre_scores_gemma":[0.7733667,0.000002830809,0.2254465,0.000751526,0.0001910056,0.00008542607,0.00001681928,0.00001246042,0.0001267431],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8753248,"threshold_uncertainty_score":0.8337532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1677952999861552,"score_gpt":0.367221644746226,"score_spread":0.1994263447600709,"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."}}