{"id":"W7125608420","doi":"10.1109/cascon66301.2025.00085","title":"Optimizing Test Case Reduction in CI/CD Pipelines Using Integer Linear Programming","year":2025,"lang":"","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); Ontario Tech University","funders":"","keywords":"Test suite; Test case; Reduction (mathematics); System under test; Pipeline transport; Test (biology); Integer programming; Test Management Approach; Software deployment; Software","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001484263,0.0004779754,0.000492177,0.001081495,0.0004803503,0.0006789937,0.0006891529,0.0003000139,0.0000161628],"category_scores_gemma":[0.002663337,0.0004853717,0.0001500947,0.00329216,0.0001983842,0.0007330077,0.0008057541,0.0007237767,0.0000113982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003504685,"about_ca_system_score_gemma":0.0004881146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003681089,"about_ca_topic_score_gemma":0.00009393849,"domain_scores_codex":[0.9965023,0.0001731621,0.001080437,0.001154951,0.0002839709,0.0008051108],"domain_scores_gemma":[0.9973937,0.0007550437,0.0002610711,0.0009921653,0.0004637252,0.0001342525],"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":[0.00003108968,0.001030407,0.009974505,0.0004303509,0.00004272474,0.00303653,0.003680044,0.01013427,0.001209536,0.0008742694,0.003168574,0.9663877],"study_design_scores_gemma":[0.0003496858,0.0001295623,0.00002456501,0.002018478,0.00004179285,0.00337471,0.0002412192,0.9871436,0.003285602,0.002336726,0.0005303309,0.0005237579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02560368,0.0008893611,0.9623987,0.0008340954,0.001393267,0.0006302817,0.000001682027,0.007711548,0.0005373727],"genre_scores_gemma":[0.4523065,0.00001970956,0.5469691,0.0001222416,0.0001665478,0.00002183633,0.000001091495,0.00001942545,0.0003735268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9770093,"threshold_uncertainty_score":0.9997598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04453385423626503,"score_gpt":0.3327682209964264,"score_spread":0.2882343667601614,"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."}}