{"id":"W4402571068","doi":"10.1109/icstw60967.2024.00031","title":"Replay-Based Continual Learning for Test Case Prioritization","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Prioritization; Computer science; Test (biology); Software engineering; Artificial intelligence; Machine learning; Process management; Engineering","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":[0.0003637027,0.00007507027,0.00006979563,0.00009269576,0.000120732,0.0003273999,0.0001490581,0.00004025468,0.00000447247],"category_scores_gemma":[0.001278174,0.00006686661,0.00004047901,0.0002535353,0.00001417955,0.000172193,0.00004021029,0.00008472949,0.000011194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002235031,"about_ca_system_score_gemma":0.00007246582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003781353,"about_ca_topic_score_gemma":0.000003502698,"domain_scores_codex":[0.9993439,0.00001836685,0.0001249558,0.0002841733,0.00008514791,0.0001435038],"domain_scores_gemma":[0.9980776,0.001575639,0.00002204055,0.0002022499,0.00008585968,0.0000366611],"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":[0.000008420404,0.0001291406,0.0116067,0.0003965162,0.00002231899,0.002856129,0.001021621,0.0006913556,0.001098415,0.06621303,0.2494619,0.6664945],"study_design_scores_gemma":[0.00009924626,0.0001828898,0.00003802524,0.00008492589,0.000004912765,0.0005188346,0.000003376854,0.9770811,0.002455575,0.007724454,0.0116754,0.0001312596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001317102,0.00007724289,0.9711504,0.0004795388,0.0001746081,0.0001438399,0.000001222463,0.02600542,0.0006506082],"genre_scores_gemma":[0.6111028,4.042576e-7,0.3879505,0.000151299,0.00005095831,0.00002838185,0.000003409061,0.000008625791,0.0007036403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9763898,"threshold_uncertainty_score":0.3157125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01782511303937027,"score_gpt":0.2913492331547891,"score_spread":0.2735241201154188,"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."}}