{"id":"W2956106249","doi":"10.1109/icse-companion.2019.00055","title":"An Empirical Study on Leveraging Logs for Debugging Production Failures","year":2019,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Debugging; Computer science; Software bug; TRACE (psycholinguistics); Snapshot (computer storage); Software engineering; Software; Algorithmic program debugging; Software maintenance; Process (computing); Programming language; Software development; Operating system","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":[0.0006237167,0.0001011034,0.0001330268,0.00007482398,0.0001251975,0.000100595,0.0003743175,0.00003585938,0.000008155937],"category_scores_gemma":[0.00003572034,0.00007033749,0.0000419138,0.000170111,0.000009330206,0.0005792571,0.00005181363,0.00007586976,0.00009063575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004519122,"about_ca_system_score_gemma":0.00004205422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002815105,"about_ca_topic_score_gemma":0.000007055769,"domain_scores_codex":[0.9988378,0.00005843218,0.0001713703,0.0005210566,0.0002096102,0.0002016996],"domain_scores_gemma":[0.9990539,0.00006717932,0.0000402349,0.0007129306,0.0000801163,0.00004564624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002731219,0.0005837486,0.9688941,0.00005279588,0.00002113527,8.96961e-7,0.005261693,0.001762211,0.0004936597,0.0003093148,0.001728926,0.02086416],"study_design_scores_gemma":[0.001612483,0.003714165,0.8310269,0.0000663846,0.0000161412,0.0000197166,0.00255074,0.1465623,0.006825231,0.001548078,0.005364718,0.0006931159],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8667161,0.000004379299,0.1297903,0.001066129,0.0009589752,0.0008733052,1.294379e-7,0.000390469,0.0002002441],"genre_scores_gemma":[0.9936068,1.74634e-7,0.005707368,0.0002208132,0.0001311622,0.00004864467,8.114927e-7,0.00000627138,0.0002779643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1448001,"threshold_uncertainty_score":0.286828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03084799510920925,"score_gpt":0.3252834830562689,"score_spread":0.2944354879470596,"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."}}