{"id":"W4281811500","doi":"10.1007/s10664-022-10153-2","title":"Works for Me! Cannot Reproduce – A Large Scale Empirical Study of Non-reproducible Bugs","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Dalhousie University","funders":"","keywords":"Software bug; Computer science; Empirical research; Software; Debugging; Eclipse; Software regression; Software engineering; Data science; Software development; Software quality; Programming language; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002208947,0.0003918807,0.0006281553,0.0004897033,0.0003619581,0.0001182216,0.001955052,0.0001060516,0.00004576669],"category_scores_gemma":[0.004290054,0.000423033,0.000216743,0.002581741,0.00002544361,0.0003590977,0.001950752,0.0008819022,0.00001037141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003669159,"about_ca_system_score_gemma":0.000212388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004797324,"about_ca_topic_score_gemma":0.000005991198,"domain_scores_codex":[0.99522,0.0001027231,0.0006953324,0.001669237,0.001222535,0.001090144],"domain_scores_gemma":[0.9952249,0.001806424,0.0001204191,0.002301301,0.0002388681,0.0003080842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009647931,0.002618855,0.6198634,0.0002693265,0.00020189,0.00008492649,0.01250854,0.3434747,0.000689997,0.00001693142,0.0168602,0.003314769],"study_design_scores_gemma":[0.006819954,0.004710219,0.6002888,0.0001736819,0.00009818013,0.0001497943,0.001407999,0.3225555,0.004688233,0.0001521292,0.05635874,0.002596691],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.53509,0.0002162645,0.4621003,0.0003252205,0.0006807381,0.0008374681,0.00001664942,0.0007296824,0.000003695502],"genre_scores_gemma":[0.9465175,0.000002103191,0.05170557,0.0001150384,0.0002589962,0.001057145,0.00001293506,0.00009773696,0.0002330417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4114275,"threshold_uncertainty_score":0.9998221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03099162961572883,"score_gpt":0.3207328907301085,"score_spread":0.2897412611143796,"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."}}