{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001513851,0.001507815,0.0007442328,0.007306395,0.0003050873,0.0009955975,0.001353525,0.000855348,0.001203021],"category_scores_gemma":[0.01090254,0.0004292275,0.0007023932,0.002799863,0.0002820255,0.001594227,0.0004916359,0.0008193966,0.001116467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005946842,"about_ca_system_score_gemma":0.0008743698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007149105,"about_ca_topic_score_gemma":0.01076051,"domain_scores_codex":[0.9989119,0.0001760604,0.000134448,0.0002663775,0.0003942187,0.0001170397],"domain_scores_gemma":[0.9892628,0.005144277,0.001557591,0.001393128,0.002200718,0.0004415183],"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":[0.0008548995,0.00106663,0.2409158,0.0008868311,0.0003074244,0.001670951,0.0003437774,0.1390432,0.01944749,0.001166822,0.02098403,0.5733122],"study_design_scores_gemma":[0.00005169573,0.0003936243,0.04566069,0.00009019455,0.0001107359,0.0006784762,0.0002351624,0.927403,0.01539132,0.00365709,0.006275391,0.00005248533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6593813,0.003044797,0.261408,0.0009219861,0.0002314756,0.0004647234,0.02833057,0.04282421,0.003392964],"genre_scores_gemma":[0.8572738,0.0006561624,0.1058556,0.0001399564,0.00009033542,0.0002015755,0.0336836,0.0004835955,0.001615438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007306395,"threshold_uncertainty_score":0.01421499,"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."}}