{"id":"W2895807070","doi":"10.1145/3273934.3273944","title":"An Improvement to Test Case Failure Prediction in the Context of Test Case Prioritization","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); Toronto Metropolitan University","funders":"","keywords":"Computer science; Test (biology); Test suite; Ranking (information retrieval); Context (archaeology); Test plan; Machine learning; Test case; A priori and a posteriori; Scale (ratio); Predictive modelling; Data mining; Logistic regression; Reliability (semiconductor); Plan (archaeology); Artificial intelligence; Reliability engineering; Regression analysis; Statistics; Engineering","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":[0.01273674,0.002684397,0.001700545,0.004071419,0.0006519725,0.002552394,0.00368253,0.00173873,0.002832822],"category_scores_gemma":[0.08917016,0.0007750346,0.001949845,0.003896847,0.0007162147,0.004750398,0.00170904,0.004170041,0.001366405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001297773,"about_ca_system_score_gemma":0.002275161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01377971,"about_ca_topic_score_gemma":0.01110461,"domain_scores_codex":[0.9892609,0.005151425,0.0007099504,0.00272593,0.001809407,0.0003423998],"domain_scores_gemma":[0.9109246,0.06552245,0.005326409,0.008882963,0.008515402,0.0008282391],"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":[0.0009592696,0.001393,0.1120677,0.0008687533,0.0009008819,0.0004119699,0.0005221493,0.2958758,0.003879811,0.004542945,0.01090189,0.5676758],"study_design_scores_gemma":[0.00005408046,0.0002612297,0.008074513,0.0000748029,0.0001337361,0.0001973847,0.00007402172,0.9838023,0.001162904,0.003909566,0.002213118,0.00004233068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1327297,0.002657775,0.8456762,0.004858567,0.0003728139,0.0005222702,0.002485456,0.007111472,0.003585819],"genre_scores_gemma":[0.6755542,0.0007320447,0.3181435,0.0006315005,0.0004368653,0.0002471142,0.002853022,0.0003179025,0.001083782],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01377971,"threshold_uncertainty_score":0.06735909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01481317464007329,"score_gpt":0.2750601831074138,"score_spread":0.2602470084673404,"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."}}