{"id":"W2074019008","doi":"10.1145/2597073.2597098","title":"Works for me! characterizing non-reproducible bug reports","year":2014,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software bug; Root cause; Software regression; Software; Set (abstract data type); Software engineering; Software quality; Software development; Reliability engineering; Programming language; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001289445,0.00009981654,0.0001342457,0.0001045078,0.00007649023,0.0002369195,0.0004878406,0.00004954674,0.00001482245],"category_scores_gemma":[0.001421848,0.00008977488,0.0000537686,0.0002834759,0.00001271407,0.0004105467,0.0002308758,0.0001099044,0.00004121263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002755309,"about_ca_system_score_gemma":0.00003674589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000133357,"about_ca_topic_score_gemma":8.187217e-7,"domain_scores_codex":[0.998582,0.00001270391,0.0001953471,0.0006072248,0.0002346048,0.0003681341],"domain_scores_gemma":[0.9979595,0.0004575445,0.00004605844,0.001328154,0.0001056041,0.0001031279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003222859,0.0003294665,0.07873626,0.0004771695,0.0001460726,0.0001453378,0.002039638,0.002196586,0.1512225,0.01953269,0.06740062,0.6777415],"study_design_scores_gemma":[0.0009483626,0.0004410839,0.1632171,0.000288044,0.0000115051,0.0002900656,0.00001967018,0.3952971,0.2623101,0.005779776,0.1700427,0.001354591],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05705583,0.00002169096,0.9396861,0.00105579,0.0007664324,0.0002309742,1.212732e-7,0.0004960257,0.0006870647],"genre_scores_gemma":[0.8507116,0.000002204872,0.1468537,0.0002040624,0.0002742216,0.00008398044,0.000002098871,0.00001732014,0.001850726],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7936558,"threshold_uncertainty_score":0.3660913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01862152233759597,"score_gpt":0.2678200077974596,"score_spread":0.2491984854598636,"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."}}