{"id":"W4411058752","doi":"10.1145/3727582.3728681","title":"Leveraging LLM Enhanced Commit Messages to Improve Machine Learning Based Test Case Prioritization","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); Ontario Tech University","funders":"","keywords":"Commit; Prioritization; Computer science; Test (biology); Machine learning; Artificial intelligence; Process management; Engineering; Database","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":[0.0004152532,0.0001529513,0.0001558852,0.0002359299,0.0003011132,0.0002520606,0.0004224522,0.00005176669,0.00001043444],"category_scores_gemma":[0.001575932,0.0001469757,0.0000381704,0.0007155244,0.0000164978,0.0001808805,0.0002713283,0.0001945031,0.00001136751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006844753,"about_ca_system_score_gemma":0.00008155649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004366867,"about_ca_topic_score_gemma":0.0000262387,"domain_scores_codex":[0.9989036,0.00006790031,0.0002146829,0.00041941,0.0001483825,0.0002460808],"domain_scores_gemma":[0.9982617,0.000983744,0.00005764818,0.0004791008,0.0001445494,0.00007323737],"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":[0.00002076946,0.0005625333,0.05068899,0.0002821005,0.00004540868,0.0008629817,0.00196614,0.005790497,0.02946756,0.005881675,0.02760991,0.8768215],"study_design_scores_gemma":[0.0004147611,0.0002251645,0.0008203891,0.0002057756,0.00001085303,0.00005408515,0.00001574838,0.8961262,0.09605478,0.004415614,0.001295454,0.0003612332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005018561,0.00003817531,0.9791374,0.001529442,0.0001514952,0.0002070393,0.000001120216,0.01103935,0.002877433],"genre_scores_gemma":[0.6895863,9.598958e-7,0.3079568,0.001243381,0.00001411449,0.00002623183,0.000002385945,0.000007544597,0.001162271],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8903356,"threshold_uncertainty_score":0.5993494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01080975645387326,"score_gpt":0.2664477481246184,"score_spread":0.2556379916707451,"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."}}