{"id":"W4406866174","doi":"10.1145/3715008","title":"Scalable Similarity-Aware Test Suite Minimization with Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test suite; Reinforcement learning; Suite; Scalability; Minification; Similarity (geometry); Test (biology); Artificial intelligence; Software engineering; Machine learning; Test case; Programming language; Operating system","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":[0.001930379,0.001730246,0.001463363,0.001130426,0.0003786787,0.0007656215,0.002193855,0.001101912,0.002620896],"category_scores_gemma":[0.009485103,0.0006529322,0.001157441,0.0008268983,0.001069268,0.001361667,0.001498418,0.002104428,0.0005334596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221734,"about_ca_system_score_gemma":0.001960493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003827803,"about_ca_topic_score_gemma":0.004920663,"domain_scores_codex":[0.9979813,0.0007610918,0.00009571987,0.0004009521,0.0005335513,0.0002273829],"domain_scores_gemma":[0.9937338,0.004419322,0.0005119772,0.0005177365,0.0005641155,0.0002530183],"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":[0.0001349174,0.000288717,0.002144379,0.000179478,0.00006627223,0.0001252677,0.00005540004,0.8540623,0.004427793,0.002728469,0.002903448,0.1328836],"study_design_scores_gemma":[0.00002497187,0.00005504497,0.0001352949,0.000006006191,0.00000844138,0.00002034236,0.000008706248,0.9959083,0.000779764,0.002829317,0.0002205291,0.000003235823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07953009,0.0006459709,0.909829,0.000604361,0.00005819518,0.0003013119,0.0002484203,0.005888473,0.00289415],"genre_scores_gemma":[0.7348679,0.0001436035,0.2606792,0.000413698,0.00005686888,0.0004450493,0.001086954,0.0005576891,0.001749097],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003827803,"threshold_uncertainty_score":0.01020896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04087899492526334,"score_gpt":0.2917156633049735,"score_spread":0.2508366683797102,"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."}}