{"id":"W4404199042","doi":"10.1007/s10664-024-10579-w","title":"Towards enhancing the reproducibility of deep learning bugs: an empirical study","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Dalhousie University","funders":"","keywords":"Reproducibility; Empirical research; Computer science; Data science; Artificial intelligence; Statistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.004156473,0.0003094723,0.000401739,0.0001672212,0.0002187557,0.000256509,0.001277916,0.0001165001,0.00003468804],"category_scores_gemma":[0.008217238,0.0002304709,0.0001662053,0.001348535,0.00005541886,0.0006687381,0.0008503298,0.001269931,0.00001999675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001619082,"about_ca_system_score_gemma":0.0001125503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005873099,"about_ca_topic_score_gemma":0.00001081191,"domain_scores_codex":[0.9962478,0.0003926616,0.0006420213,0.001546666,0.0006801281,0.0004907625],"domain_scores_gemma":[0.9965321,0.001247908,0.00008202429,0.001872698,0.0001053689,0.000159937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001274807,0.0002494708,0.1852602,0.0001792392,0.000126168,0.0001208493,0.02273142,0.7102042,0.0002972497,0.0002739922,0.000059848,0.08048464],"study_design_scores_gemma":[0.0002087315,0.0004474057,0.1693359,0.00008679603,0.00004438815,0.00003529135,0.0004595938,0.8249425,0.0006476879,0.0003127729,0.003012308,0.0004666966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3369934,0.000362176,0.6601977,0.0003568415,0.000683187,0.0002092657,3.777339e-7,0.001167852,0.00002921431],"genre_scores_gemma":[0.9516475,0.000002438131,0.04778844,0.00006302581,0.0003836767,0.00002915786,0.000002080543,0.00004624359,0.00003740596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6146542,"threshold_uncertainty_score":0.9837395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02200891701765622,"score_gpt":0.3207673699558249,"score_spread":0.2987584529381687,"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."}}