{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04733225,0.0009916887,0.001008932,0.008376349,0.001400037,0.0101082,0.002082111,0.002350604,0.0009282849],"category_scores_gemma":[0.26471,0.0009336575,0.0007219394,0.005377555,0.003414407,0.01297201,0.003643274,0.004223877,0.000565781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101873,"about_ca_system_score_gemma":0.004295089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01196719,"about_ca_topic_score_gemma":0.02515512,"domain_scores_codex":[0.9721272,0.01589537,0.002393226,0.001729972,0.007252817,0.0006014752],"domain_scores_gemma":[0.629755,0.2547865,0.02270295,0.0480988,0.04200588,0.002650988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003594563,0.0005535735,0.4773143,0.001092061,0.000574046,0.0004860676,0.01184959,0.008340313,0.0119555,0.02380886,0.01082252,0.4528438],"study_design_scores_gemma":[0.0001260346,0.0008305135,0.4945247,0.002574582,0.0006652569,0.002593041,0.02302497,0.2511702,0.01802444,0.1621795,0.04370211,0.0005846846],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.537558,0.007896166,0.3937184,0.0456034,0.001066954,0.0004415299,0.002562356,0.002878298,0.008274945],"genre_scores_gemma":[0.807378,0.001486363,0.1863263,0.001485193,0.000523926,0.0001247818,0.001035554,0.0003079371,0.001332005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04733225,"threshold_uncertainty_score":0.2503199,"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."}}