{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005268771,0.0007383462,0.0004743928,0.006375398,0.0009915135,0.002120631,0.001093724,0.0009427973,0.004859465],"category_scores_gemma":[0.05173164,0.0005524718,0.0006125636,0.004794195,0.0007062837,0.002337936,0.001349433,0.0006413293,0.005396794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004551848,"about_ca_system_score_gemma":0.0006320004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00174182,"about_ca_topic_score_gemma":0.00310795,"domain_scores_codex":[0.9945719,0.0014402,0.0004577231,0.0009009253,0.002351555,0.0002776211],"domain_scores_gemma":[0.9314417,0.02536655,0.02028502,0.009465554,0.01139131,0.002049799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000357547,0.0002956532,0.5540045,0.0009520041,0.0003185216,0.001072156,0.003754512,0.001316198,0.006561384,0.002264368,0.05994545,0.3691576],"study_design_scores_gemma":[0.00009695292,0.0008612196,0.8400041,0.0007571472,0.0002817158,0.004617736,0.004758136,0.0113754,0.008463904,0.007916838,0.1206508,0.0002161232],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9018194,0.00479523,0.04344129,0.007048874,0.0005296199,0.0006280065,0.01766774,0.004842399,0.01922758],"genre_scores_gemma":[0.9217926,0.001796747,0.04865688,0.001291072,0.0003040869,0.0004666763,0.01265937,0.001222381,0.01181032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006375398,"threshold_uncertainty_score":0.02786422,"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."}}