{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005142694,0.000085312,0.0000799086,0.000105189,0.0001084841,0.00009269456,0.0003121805,0.00004183452,0.000005006295],"category_scores_gemma":[0.0006553628,0.0000612642,0.00001509147,0.0004603211,0.00003367746,0.0002519021,0.00007264859,0.00006401203,0.00000608803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003413406,"about_ca_system_score_gemma":0.00003582626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001975558,"about_ca_topic_score_gemma":0.002086782,"domain_scores_codex":[0.9992105,0.00003806506,0.0002197108,0.0002426582,0.0001493849,0.0001396657],"domain_scores_gemma":[0.9987136,0.0004232213,0.000059606,0.0005554574,0.0001979426,0.00005024364],"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":[0.00001749281,0.003067855,0.1914436,0.0001049288,0.00001488689,0.007326385,0.04027952,0.00003749113,0.02161501,0.008042913,0.1069675,0.6210825],"study_design_scores_gemma":[0.002143727,0.03097173,0.0147872,0.0004445594,0.00004770959,0.0548413,0.004714524,0.750606,0.121959,0.01495976,0.00326342,0.001261045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4228825,0.000005306745,0.5724485,0.001124079,0.0001043347,0.000571868,0.00001639037,0.002583213,0.0002638206],"genre_scores_gemma":[0.9166899,2.252332e-7,0.08255574,0.0006293656,0.00006820186,0.00003163752,0.000001777942,0.000004807799,0.00001829965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7505685,"threshold_uncertainty_score":0.2986465,"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."}}