{"id":"W4384345700","doi":"10.1109/icse48619.2023.00122","title":"GameRTS: A Regression Testing Framework for Video Games","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regression testing; Game design; Test suite; Sequential game; Video game; Context (archaeology); Game testing; Game Developer; Regression analysis; Software; Machine learning; Artificial intelligence; Test case; Software development; Game theory; Game design document; Programming language; Software construction; Multimedia","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0122761,0.002572714,0.00129493,0.004585228,0.0006544408,0.002506213,0.005444078,0.00179879,0.005180526],"category_scores_gemma":[0.04098045,0.00161798,0.003545361,0.001241964,0.002177944,0.003828302,0.003382905,0.003354123,0.001479306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001497514,"about_ca_system_score_gemma":0.003062001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01010132,"about_ca_topic_score_gemma":0.008982886,"domain_scores_codex":[0.9879839,0.005079825,0.001426715,0.001843877,0.003019877,0.0006457391],"domain_scores_gemma":[0.980731,0.01260652,0.001967477,0.002127417,0.00201392,0.0005535905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001130511,0.001140067,0.03364904,0.002663556,0.001043009,0.002160357,0.002669828,0.2655888,0.0327628,0.09787387,0.03538381,0.5239343],"study_design_scores_gemma":[0.0001744686,0.0004071814,0.002683566,0.0002837352,0.0001091865,0.0007513146,0.000147603,0.9299191,0.01094126,0.03218303,0.02226537,0.0001342052],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004471511,0.0002242553,0.9430333,0.000182806,0.00004792057,0.0005511959,0.0004214138,0.05015135,0.0009162607],"genre_scores_gemma":[0.1532527,0.000329116,0.8349888,0.0003255728,0.00008626153,0.001298419,0.001937562,0.006085637,0.001696007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0122761,"threshold_uncertainty_score":0.06492299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07865055184339448,"score_gpt":0.3418979753851524,"score_spread":0.2632474235417579,"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."}}