{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009581443,0.001095845,0.0007799289,0.006377416,0.0005478165,0.00180824,0.001389963,0.00143221,0.001007706],"category_scores_gemma":[0.08137291,0.0004704265,0.0005369549,0.003043244,0.0008685245,0.002327587,0.001342247,0.001189871,0.0004577671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001124055,"about_ca_system_score_gemma":0.00120098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009318043,"about_ca_topic_score_gemma":0.01543841,"domain_scores_codex":[0.9890342,0.003450499,0.00101316,0.002147917,0.003488645,0.0008656254],"domain_scores_gemma":[0.8529387,0.09791256,0.02279044,0.006959769,0.01636243,0.003035972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001101541,0.0005767107,0.7939063,0.0006762834,0.000480063,0.0007421352,0.002010904,0.06533787,0.01914047,0.001383934,0.003322209,0.1113215],"study_design_scores_gemma":[0.0001200862,0.00178228,0.6705958,0.0003056993,0.0003597461,0.001357221,0.002443148,0.2842744,0.02969243,0.003622446,0.005273493,0.0001733164],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.978157,0.0008002734,0.01805592,0.0002073956,0.00002999579,0.00006067504,0.0007209269,0.0008097748,0.001158016],"genre_scores_gemma":[0.9813629,0.0001219633,0.01671947,0.00005529502,0.00001321986,0.00005012219,0.001030338,0.000161077,0.0004854918],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009581443,"threshold_uncertainty_score":0.05067211,"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."}}