{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01435488,0.0004890239,0.0003170774,0.002732625,0.0005077958,0.001684113,0.001352551,0.001045006,0.001242986],"category_scores_gemma":[0.1488947,0.000388414,0.0002850455,0.002650298,0.0007515387,0.00391614,0.0009530326,0.001342248,0.0005411354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005132804,"about_ca_system_score_gemma":0.0007788627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002527865,"about_ca_topic_score_gemma":0.003533125,"domain_scores_codex":[0.9837902,0.01082365,0.001373519,0.0009453598,0.002599005,0.000468242],"domain_scores_gemma":[0.6083895,0.3270484,0.02944465,0.0153495,0.01716084,0.002607164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007889236,0.002527124,0.8896426,0.0005260755,0.000123177,0.0005455586,0.008070469,0.001511245,0.002311343,0.000697677,0.002200735,0.09105515],"study_design_scores_gemma":[0.0001373195,0.003594913,0.8884096,0.0004882619,0.0002777674,0.002421212,0.02665641,0.05291023,0.007963036,0.001200249,0.01577778,0.0001632096],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932468,0.0002587183,0.003848265,0.0002647284,0.00001723122,0.0001639834,0.0007952041,0.0001417316,0.001263276],"genre_scores_gemma":[0.9938301,0.0001694962,0.004605547,0.00005158637,0.00001383887,0.00008149786,0.0008235055,0.00003168496,0.0003927283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01435488,"threshold_uncertainty_score":0.07591677,"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."}}