{"id":"W3095252018","doi":"10.1109/tse.2021.3070549","title":"Reinforcement Learning for Test Case Prioritization","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Queen's University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Reinforcement learning; Computer science; Prioritization; Context (archaeology); Ranking (information retrieval); Regression testing; Machine learning; Test case; Bidding; Test (biology); Adaptation (eye); Artificial intelligence; Regression analysis; Engineering; Software; Software system","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002797195,0.000405057,0.0003492502,0.0003505857,0.000295044,0.0004189533,0.0004526643,0.000312039,0.000007068882],"category_scores_gemma":[0.0005500963,0.0004913202,0.0002532813,0.0003406516,0.00001389082,0.0002361854,0.0000253626,0.0009365158,0.000003434618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002492559,"about_ca_system_score_gemma":0.000168472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005249189,"about_ca_topic_score_gemma":0.00000390789,"domain_scores_codex":[0.9981565,0.00002627015,0.0004245692,0.0007222977,0.0002814671,0.0003888541],"domain_scores_gemma":[0.9974702,0.001205701,0.0001369494,0.0007876446,0.0002737464,0.0001257651],"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":[0.000001887944,0.00005046839,0.00002401847,0.0003175165,0.00003930995,0.0001895527,0.0003315965,0.9781109,0.00004115524,0.00002122643,0.0001653962,0.02070697],"study_design_scores_gemma":[0.0002389825,0.0001636157,0.00001358576,0.0008316787,0.00005158219,0.0005545792,0.000007934848,0.9898067,0.007290993,0.0001280536,0.000285338,0.000627008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009662138,0.0001093496,0.9789068,0.00003232632,0.001617954,0.0005267368,0.00001016754,0.01782404,0.00000639891],"genre_scores_gemma":[0.5118025,0.00002586056,0.4874932,0.00003799506,0.00007391062,0.0003816146,0.00001751992,0.00005288286,0.0001145908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5108362,"threshold_uncertainty_score":0.9997538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01940539093767392,"score_gpt":0.2513335815788734,"score_spread":0.2319281906411994,"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."}}