{"id":"W4396786304","doi":"10.1145/3663529.3663850","title":"Easy over Hard: A Simple Baseline for Test Failures Causes Prediction","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Ningbo; Zhejiang University; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Root cause analysis; Abstraction; Root cause; Table (database); Software bug; Test (biology); Test case; Data mining; Test data; Parsing; Software; Reliability engineering; Machine learning; Artificial intelligence; Programming language; 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":[0.0009072211,0.0003235748,0.0003629469,0.0001679749,0.0001195596,0.0004612876,0.000933704,0.0003466765,0.00006537282],"category_scores_gemma":[0.0003766096,0.0002370362,0.000289152,0.0002146421,0.0000402864,0.0002121961,0.00190244,0.0004113122,0.0001193706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329075,"about_ca_system_score_gemma":0.0003209935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004651492,"about_ca_topic_score_gemma":0.0001104533,"domain_scores_codex":[0.9976102,0.00003433614,0.0005344646,0.001122002,0.0003635623,0.0003354042],"domain_scores_gemma":[0.9976997,0.0004302361,0.0001210906,0.00140345,0.0002376937,0.0001077976],"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":[0.00005335657,0.0006925159,0.1131755,0.01353094,0.0005505541,0.00003014789,0.001585066,0.007622201,0.000467801,0.01669174,0.8113545,0.03424571],"study_design_scores_gemma":[0.0004324947,0.000212471,0.008877035,0.0004808705,0.0000898038,0.00001740716,0.00002530557,0.7667038,0.001168197,0.05144604,0.1699105,0.0006360605],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02104919,0.0008797749,0.9613976,0.002362513,0.007176926,0.002332112,0.0007406765,0.003062212,0.0009990091],"genre_scores_gemma":[0.9317639,0.0001126165,0.05345573,0.0007190652,0.002550419,0.001379375,0.0002917339,0.00007705116,0.009650094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9107147,"threshold_uncertainty_score":0.9666056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01968101535446119,"score_gpt":0.2757080627797608,"score_spread":0.2560270474252996,"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."}}