{"id":"W3195614596","doi":"10.1145/3468264.3473930","title":"Quantifying no-fault-found test failures to prioritize inspection of flaky tests at Ericsson","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reliability engineering; Fault (geology); Test (biology); Fault coverage; Work (physics); Software; Computer science; Software testing; Engineering; Embedded system; Operating system; Electrical engineering; Geology; Mechanical engineering; Seismology","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":[0.0002544979,0.0001479707,0.000206998,0.0001281549,0.0001693576,0.0001501453,0.0004575533,0.00007163964,0.0000194367],"category_scores_gemma":[0.003098427,0.0001429856,0.00006372945,0.0008452566,0.00003361907,0.0002363165,0.0005403003,0.0001053092,0.0001093605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001057993,"about_ca_system_score_gemma":0.00009640923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003731548,"about_ca_topic_score_gemma":0.0003127753,"domain_scores_codex":[0.9986294,0.0000397313,0.0002864946,0.0004669206,0.0003180891,0.0002593581],"domain_scores_gemma":[0.9978652,0.0007815461,0.00009399022,0.0007180376,0.0004389446,0.0001022602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002551419,0.0006988262,0.4312366,0.0003064131,0.0000495664,0.0002513678,0.001832883,0.0001670857,0.2731276,0.01803677,0.2175743,0.05669304],"study_design_scores_gemma":[0.001145719,0.001588077,0.3470119,0.001132932,0.00004162586,0.0007718184,0.00008150697,0.06514236,0.5171142,0.02366946,0.04028363,0.002016811],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2608125,0.0002704749,0.6978723,0.002626027,0.001105137,0.0003759207,0.000006554378,0.02781499,0.009116041],"genre_scores_gemma":[0.5825407,0.000005334114,0.4165913,0.0002475882,0.00005576806,0.000008962093,0.000001667243,0.000009893339,0.0005388283],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3217282,"threshold_uncertainty_score":0.5830784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03981080436858048,"score_gpt":0.308410739023143,"score_spread":0.2685999346545625,"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."}}