{"id":"W2953988581","doi":"10.1109/icse-companion.2019.00095","title":"Supervised Tie Breaking in Test Case Prioritization","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Prioritization; Test (biology); Test case; Code coverage; Rank (graph theory); Data mining; Code (set theory); Cover (algebra); Reliability engineering; Machine learning; Software; Engineering; Mathematics; Programming language; Regression analysis","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":[0.0002064386,0.00006548382,0.00007742754,0.0001088054,0.00003197513,0.00008888826,0.0002383919,0.00003738146,0.00001766436],"category_scores_gemma":[0.0001962186,0.0000609889,0.00001556933,0.0003528623,0.000007317552,0.0002702379,0.0001085323,0.00006495188,0.00005906317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012575,"about_ca_system_score_gemma":0.00003250729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004637935,"about_ca_topic_score_gemma":0.0000320689,"domain_scores_codex":[0.9994027,0.00001885103,0.0001242326,0.0002137537,0.00009618691,0.0001442999],"domain_scores_gemma":[0.9992325,0.0003284597,0.00002313135,0.0003487219,0.00003934225,0.00002781499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001617467,0.0001371684,0.7808908,0.00004455859,0.000002411444,0.001053274,0.0009441702,0.00004933884,0.0008094914,0.01238069,0.004005348,0.1996811],"study_design_scores_gemma":[0.0009048273,0.0002557189,0.03308877,0.0002485373,0.000003146716,0.003478594,0.00002898018,0.9171303,0.003611109,0.03976081,0.0008352531,0.0006539607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3829471,0.00004239369,0.5902582,0.0003981083,0.0002156697,0.000294247,6.657478e-7,0.01354191,0.01230175],"genre_scores_gemma":[0.8361763,5.565216e-7,0.1634077,0.0002322299,0.00001217326,0.000004346861,6.767929e-7,0.000004822195,0.0001611308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9170809,"threshold_uncertainty_score":0.2487055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.011334825375838,"score_gpt":0.2420150815609072,"score_spread":0.2306802561850692,"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."}}