{"id":"W4312429593","doi":"10.1109/icsme55016.2022.00039","title":"What Made This Test Flake? Pinpointing Classes Responsible for Test Flakiness","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Regression testing; Code (set theory); Quality (philosophy); Fault (geology); Test (biology); Test suite; Class (philosophy); Reliability engineering; Debugging; Test case; Programming language; Software; Machine learning; Artificial intelligence; Software development; Engineering; Regression analysis","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":[0.001147837,0.0001972977,0.0002143196,0.0002392131,0.0007920637,0.0007017023,0.001342721,0.00004803716,0.00009527806],"category_scores_gemma":[0.003831444,0.0001897443,0.0001005501,0.0008497089,0.00004379709,0.000916527,0.001018453,0.0002264401,0.0000232924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009420259,"about_ca_system_score_gemma":0.0002365798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006525146,"about_ca_topic_score_gemma":0.00001094796,"domain_scores_codex":[0.9981798,0.00007523078,0.000316426,0.000595593,0.0003746663,0.0004582793],"domain_scores_gemma":[0.9926658,0.006081781,0.0001456369,0.000861792,0.0001616665,0.00008332886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003283675,0.0006246232,0.02445846,0.0001251075,0.00002285175,0.00007938822,0.001315504,0.0001293037,0.01029677,0.02573164,0.8271123,0.1100712],"study_design_scores_gemma":[0.001612518,0.002720493,0.005546466,0.0004174478,0.00004503049,0.0007940058,0.0003964604,0.3412027,0.06326997,0.2677144,0.3140107,0.002269748],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008024589,0.0005865993,0.9087825,0.02018498,0.002753943,0.0012006,0.00002607854,0.05075511,0.007685624],"genre_scores_gemma":[0.2541175,0.00001692615,0.7278015,0.003067401,0.0001918786,0.0005834787,0.00001130274,0.00004970678,0.01416036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5131015,"threshold_uncertainty_score":0.7737549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03059816568578549,"score_gpt":0.2858525494159046,"score_spread":0.2552543837301191,"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."}}