{"id":"W3119029787","doi":"10.1007/s10664-020-09893-w","title":"Demystifying the challenges and benefits of analyzing user-reported logs in bug reports","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba; Concordia University","funders":"","keywords":"Debugging; Computer science; Software bug; Security bug; Process (computing); Software engineering; World Wide Web; Data science; Software; Programming language; Computer security","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":[0.0007220297,0.0001583107,0.0003119921,0.00009370992,0.00005847064,0.00004008003,0.0002194976,0.0001072622,0.000002394172],"category_scores_gemma":[0.001277984,0.0001189905,0.00007069768,0.000553222,0.00002730321,0.0002549277,0.0002941563,0.0002335114,0.00000101355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004690309,"about_ca_system_score_gemma":0.0000664313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002120536,"about_ca_topic_score_gemma":0.00001899737,"domain_scores_codex":[0.9984164,0.00004586829,0.0005521151,0.0004454886,0.0002566154,0.0002835103],"domain_scores_gemma":[0.9985342,0.0005309871,0.0001272027,0.0006194586,0.0001095337,0.00007864412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002373795,0.00005954798,0.940892,0.000359601,0.00005437132,0.0002969734,0.002157182,0.03136891,0.000104162,0.0003192146,0.00003229833,0.0243533],"study_design_scores_gemma":[0.0001568134,0.00002250234,0.9903914,0.0002987082,0.00001177683,0.000464415,0.00004621875,0.005713766,0.001450972,0.0002636029,0.0009557644,0.0002240145],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9057561,0.01439384,0.07831942,0.0008164968,0.0003735753,0.000111816,5.100559e-7,0.0002123548,0.00001586787],"genre_scores_gemma":[0.9886401,0.0003629636,0.0108688,0.00003956622,0.0000507428,0.0000151221,0.000001099831,0.00001179047,0.000009784892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.082884,"threshold_uncertainty_score":0.485229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03840174201774539,"score_gpt":0.2634092182250908,"score_spread":0.2250074762073455,"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."}}