{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00838257,0.002559559,0.002149629,0.003477189,0.0008322345,0.001376746,0.003846295,0.001446982,0.003141305],"category_scores_gemma":[0.03537692,0.00123112,0.001390271,0.001783858,0.001530959,0.002802556,0.002517121,0.004014003,0.000792322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002045304,"about_ca_system_score_gemma":0.003114286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009449108,"about_ca_topic_score_gemma":0.01030994,"domain_scores_codex":[0.994319,0.001926239,0.0005283233,0.001618516,0.001236143,0.0003717671],"domain_scores_gemma":[0.9685529,0.02296725,0.002104316,0.002412501,0.003213701,0.0007493666],"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":[0.0005890634,0.0007125208,0.009819996,0.0003096775,0.0002096584,0.000179816,0.0003632771,0.562035,0.003157984,0.003725443,0.003032548,0.4158651],"study_design_scores_gemma":[0.00003309853,0.00008145638,0.0003563247,0.00001219106,0.00001620894,0.00001962589,0.00001743485,0.9958046,0.0006698201,0.002687466,0.0002918445,0.000009931019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08171979,0.001146927,0.9055012,0.0006206718,0.0001060928,0.0004942878,0.0003604547,0.008087899,0.001962644],"genre_scores_gemma":[0.7391366,0.0002471401,0.256207,0.0005073919,0.0001048035,0.0008070688,0.001217633,0.0003286623,0.001443678],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009449108,"threshold_uncertainty_score":0.04433179,"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."}}