{"id":"W2955925687","doi":"10.1109/icse.2019.00031","title":"Mining Historical Test Logs to Predict Bugs and Localize Faults in the Test Logs","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Flagging; Fault (geology); Product (mathematics); Data mining; Test data; Software; Reliability engineering; Engineering; Mathematics; Software 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":[0.0006076462,0.0001471992,0.0001761252,0.0001227149,0.00006295519,0.0001022963,0.0008471625,0.00007611277,0.000006679002],"category_scores_gemma":[0.001980624,0.00009987742,0.00002620115,0.0004938775,0.00002968109,0.0001552443,0.0003152556,0.0001607657,0.00004840118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001156113,"about_ca_system_score_gemma":0.00004250809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006970458,"about_ca_topic_score_gemma":0.00003155306,"domain_scores_codex":[0.9987172,0.00004596391,0.000221858,0.0004439098,0.0002747561,0.0002962532],"domain_scores_gemma":[0.9958671,0.003324537,0.00004549883,0.0006245449,0.00004753273,0.00009073496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004063507,0.0001811668,0.7937019,0.00002229088,0.00000250262,0.00004292464,0.002184992,0.00001676743,0.0001300347,0.0008180971,0.1726805,0.0302148],"study_design_scores_gemma":[0.002700497,0.00663476,0.5077704,0.0009619997,0.00003275414,0.001025276,0.0002629139,0.2979538,0.001203155,0.04427424,0.1346485,0.002531706],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3090145,0.0004312801,0.6241236,0.02035047,0.0009449947,0.001537773,0.000005366699,0.01823039,0.02536163],"genre_scores_gemma":[0.8704572,0.000002767524,0.1260328,0.002326779,0.00004211523,0.00002370246,4.873035e-7,0.00000892935,0.001105182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5614427,"threshold_uncertainty_score":0.4072883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01633357878032961,"score_gpt":0.2420664346322286,"score_spread":0.225732855851899,"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."}}