{"id":"W2945222996","doi":"10.1109/apsec.2018.00054","title":"Why Did This Reviewed Code Crash? An Empirical Study of Mozilla Firefox","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"","keywords":"Crash; Computer science; Code review; Code refactoring; Software; Software quality; Software engineering; Code (set theory); Root cause; Software bug; Source lines of code; Software inspection; Empirical research; Computer security; Software development; Reliability engineering; Engineering; Operating system; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02057286,0.0005060647,0.0005754906,0.004684927,0.00207276,0.001915599,0.001300864,0.00136153,0.00160509],"category_scores_gemma":[0.2040111,0.0005649512,0.0003945337,0.003065804,0.002056328,0.003018391,0.001180415,0.001753339,0.0007538376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002330533,"about_ca_system_score_gemma":0.002390149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008563822,"about_ca_topic_score_gemma":0.0139684,"domain_scores_codex":[0.9825786,0.007959364,0.001827617,0.002072976,0.004749767,0.0008116874],"domain_scores_gemma":[0.5249991,0.3420792,0.07741385,0.009589222,0.0411366,0.004782044],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009251505,0.001754323,0.8575037,0.001152064,0.000191198,0.002251707,0.08037709,0.0004139682,0.002805691,0.0005590266,0.005162566,0.04690358],"study_design_scores_gemma":[0.0001019457,0.001515247,0.9392595,0.0004939886,0.0001144313,0.001818843,0.04247047,0.003295971,0.001705,0.000313665,0.008815698,0.00009533102],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985331,0.0002348148,0.0002973334,0.0001714565,0.000008872394,0.0001007285,0.0001215314,0.00001866227,0.0005133915],"genre_scores_gemma":[0.9971803,0.0003023164,0.001031443,0.0001986961,0.00002111847,0.0001623035,0.0003969879,0.00003818288,0.0006686255],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9794272,"threshold_uncertainty_score":0.1088009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05654275935009809,"score_gpt":0.3675032591262264,"score_spread":0.3109604997761283,"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."}}