{"id":"W4288723601","doi":"10.1007/s10664-022-10158-x","title":"GBGallery : A benchmark and framework for game testing","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Software engineering; Video game development; Test strategy; Software development; Game testing; Software; Database; Game Developer; Game design; Artificial intelligence; Programming language; Game design document","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":[0.0004130433,0.0001807904,0.0001984529,0.0001290258,0.0002736067,0.0001130316,0.0005326503,0.00006026732,0.000008476762],"category_scores_gemma":[0.005979451,0.0001957754,0.00006174139,0.0005906188,0.00001673447,0.000138682,0.0006909408,0.0003821112,0.000001239271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008557643,"about_ca_system_score_gemma":0.00004744748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008707528,"about_ca_topic_score_gemma":1.025389e-7,"domain_scores_codex":[0.9986637,0.00002729833,0.0002132531,0.0004474437,0.0002520745,0.0003962244],"domain_scores_gemma":[0.9954759,0.003915411,0.00005755775,0.000371898,0.00004910704,0.0001301447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000398163,0.0003928149,0.6047632,0.0005772759,0.0001464876,0.0002138216,0.004575624,0.05358941,0.0001983495,0.0187963,0.0653415,0.2513655],"study_design_scores_gemma":[0.0005824194,0.0009323744,0.07590459,0.0002524268,0.00002616197,0.0004126547,0.00001468643,0.6742082,0.0001405251,0.1922223,0.05376345,0.00154026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01790917,0.0003236558,0.9699004,0.0003750071,0.0003192176,0.0001900908,0.000005269913,0.01096515,0.00001200212],"genre_scores_gemma":[0.279937,9.603775e-7,0.7193131,0.0004150794,0.00008661759,0.0002079386,0.000002327835,0.00002342951,0.00001360441],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6206188,"threshold_uncertainty_score":0.7983487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04408833245119895,"score_gpt":0.284560538152745,"score_spread":0.240472205701546,"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."}}