{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005198114,0.0001981757,0.0002444014,0.0003549946,0.0002483352,0.0000716248,0.0003478021,0.0001346485,0.000005532685],"category_scores_gemma":[0.002325781,0.0001856024,0.00004012233,0.0005814474,0.00004033226,0.0001625594,0.00003194706,0.0003870799,0.000001849678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004637971,"about_ca_system_score_gemma":0.00005852484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000409123,"about_ca_topic_score_gemma":0.00000240603,"domain_scores_codex":[0.9988832,0.0001095516,0.0002040434,0.0003989814,0.000120325,0.0002838575],"domain_scores_gemma":[0.9949325,0.004326927,0.00004898452,0.0005229933,0.00009653943,0.00007206542],"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":[0.00004394072,0.0001097352,0.007514234,0.0002512608,0.0001223526,0.00002179733,0.0006588008,0.7208798,0.0001969489,0.001379253,0.0004772531,0.2683446],"study_design_scores_gemma":[0.002156906,0.00209883,0.006890507,0.001140158,0.0002213209,0.0002714229,0.0000632853,0.9463444,0.01854623,0.008020303,0.01277443,0.001472157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006730693,0.00008041264,0.9925721,0.0003545817,0.0001954579,0.0001362995,0.000001280381,0.005963729,0.00002309901],"genre_scores_gemma":[0.1419206,0.00004714076,0.8572,0.0002407578,0.00001069047,0.00005934378,0.000003841916,0.00001553788,0.0005020677],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2668725,"threshold_uncertainty_score":0.7568648,"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."}}