{"id":"W4312529070","doi":"10.1145/3510457.3513038","title":"The impact of flaky tests on historical test prioritization on chrome","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Prioritization; Blocking (statistics); Pipeline (software); Computer science; Test (biology); Reliability engineering; Work (physics); Code (set theory); Regression testing; Engineering; Software; Software development; Operating system; Programming language; Computer network","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":[0.01101508,0.001426051,0.0008197294,0.002837647,0.0009566762,0.003081822,0.002553259,0.001336673,0.001726268],"category_scores_gemma":[0.08414993,0.0007158888,0.0007113182,0.001848539,0.001686244,0.004283681,0.001491603,0.002367216,0.0006996355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002679256,"about_ca_system_score_gemma":0.002849243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02494034,"about_ca_topic_score_gemma":0.03012194,"domain_scores_codex":[0.9875145,0.003180971,0.0008140423,0.002735238,0.004867635,0.0008876083],"domain_scores_gemma":[0.9087146,0.05885622,0.004473641,0.01480939,0.01103899,0.002107217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002460063,0.001096576,0.1388202,0.0006630106,0.0003860267,0.0003784306,0.0005899309,0.1897071,0.02840881,0.006222616,0.02248935,0.6087779],"study_design_scores_gemma":[0.0003255453,0.001509262,0.05026031,0.0001662749,0.0002172042,0.0006474115,0.0004278643,0.8827317,0.04644234,0.005296866,0.01179274,0.0001826099],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8059204,0.005013889,0.1245089,0.002559726,0.0005646452,0.0004087143,0.001416492,0.04578007,0.01382719],"genre_scores_gemma":[0.8910775,0.0003492547,0.1032567,0.0005601422,0.00004855481,0.00006085945,0.001433673,0.001277907,0.001935401],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02494034,"threshold_uncertainty_score":0.05825406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01932153530382496,"score_gpt":0.2868846522061037,"score_spread":0.2675631169022787,"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."}}