{"id":"W2531425405","doi":"10.1007/s10664-016-9456-2","title":"Which log level should developers choose for a new logging statement?","year":2016,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Queen's University","funders":"","keywords":"Statement (logic); Logging; Computer science; Brier score; Leverage (statistics); Login; Database; Data mining; Information retrieval; Operating system; Machine learning; Forestry","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":[0.0005527308,0.0002907008,0.0003124899,0.0001335893,0.0001279203,0.00009892006,0.000759066,0.0001554996,0.00002463068],"category_scores_gemma":[0.001082004,0.0001949214,0.0001198051,0.0004988045,0.00001760144,0.0006798557,0.0002495991,0.0001501892,0.00009000645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002889838,"about_ca_system_score_gemma":0.0002895386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002194171,"about_ca_topic_score_gemma":0.000007582728,"domain_scores_codex":[0.9978303,0.00002127673,0.0004844096,0.0006138583,0.0003499492,0.0007002497],"domain_scores_gemma":[0.998212,0.0006708302,0.0000760552,0.000577123,0.0001513834,0.0003126105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001047864,0.0002287915,0.4984455,0.0009798551,0.0004048624,0.00002482805,0.003163178,0.0110518,0.001578905,0.001145894,0.07487842,0.4079932],"study_design_scores_gemma":[0.006227609,0.0006402509,0.3924212,0.001184454,0.00006857841,0.00008662456,0.00004686266,0.03617467,0.009502307,0.002350592,0.5479562,0.00334067],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03281292,0.0001143563,0.961664,0.002996464,0.0009742887,0.0003604526,0.00001111354,0.001048559,0.00001783728],"genre_scores_gemma":[0.6175734,0.00002065504,0.3805265,0.0004665479,0.00040614,0.0001237726,0.000005380797,0.00005415153,0.0008233834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5847605,"threshold_uncertainty_score":0.7948663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07458787435700132,"score_gpt":0.3073065049729828,"score_spread":0.2327186306159815,"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."}}