{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004953339,0.004769916,0.002028611,0.009043111,0.001514654,0.004312875,0.004561723,0.003266611,0.006133626],"category_scores_gemma":[0.02909861,0.0008901703,0.002263129,0.004345017,0.0008494157,0.005936942,0.003330289,0.002942404,0.005494093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001350667,"about_ca_system_score_gemma":0.003144684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01655815,"about_ca_topic_score_gemma":0.03011831,"domain_scores_codex":[0.991516,0.001286596,0.0008673093,0.003025901,0.002561864,0.0007423275],"domain_scores_gemma":[0.9799582,0.00835513,0.0009135163,0.006806738,0.003178644,0.0007877177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002623466,0.002092865,0.1360331,0.002596235,0.0009628339,0.001597319,0.0003822794,0.02902336,0.01606829,0.005554196,0.3276351,0.4754309],"study_design_scores_gemma":[0.000944528,0.001165191,0.06144195,0.0005057495,0.000613476,0.002511956,0.0007752109,0.7262927,0.03098915,0.01856545,0.1558641,0.0003305589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2143456,0.009801921,0.2814197,0.002333237,0.002031168,0.002191283,0.1979646,0.2681925,0.02171995],"genre_scores_gemma":[0.3001704,0.0009023421,0.3489489,0.001652701,0.0004291029,0.0008793543,0.3348016,0.004893949,0.007321544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01655815,"threshold_uncertainty_score":0.03292352,"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."}}