{"id":"W4405444248","doi":"10.1145/3708473","title":"Leveraging Data Characteristics for Bug Localization in Deep Learning Programs","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Deep learning; Artificial intelligence; Software engineering; Data science; Machine learning","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":[0.002018475,0.001615749,0.0008133135,0.003112985,0.0004293975,0.001081856,0.001766265,0.001284597,0.0007894096],"category_scores_gemma":[0.01609125,0.0005288823,0.0006951669,0.001745399,0.0006601294,0.002704421,0.001637141,0.002097269,0.0005103734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102085,"about_ca_system_score_gemma":0.001269054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005704511,"about_ca_topic_score_gemma":0.009396717,"domain_scores_codex":[0.9983701,0.000317777,0.0002039598,0.0004959175,0.0004369451,0.0001753506],"domain_scores_gemma":[0.9907758,0.004605382,0.001240697,0.001431235,0.001642088,0.0003048028],"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":[0.0008120402,0.001136326,0.1632457,0.0008243216,0.0002432283,0.0005885073,0.0004427618,0.2263881,0.01786003,0.002038378,0.01709382,0.5693268],"study_design_scores_gemma":[0.00003575833,0.0001446704,0.006419584,0.00003575717,0.00004618473,0.0000899009,0.00008036169,0.9788329,0.008941648,0.003175181,0.002175872,0.00002208156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6860875,0.002518733,0.2727672,0.001767032,0.0001837635,0.0002125255,0.006101637,0.02806923,0.002292416],"genre_scores_gemma":[0.8987358,0.0002928015,0.08971149,0.0003642637,0.00004575873,0.0001770461,0.00934526,0.0003481597,0.0009795935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005704511,"threshold_uncertainty_score":0.01134264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.133584645627091,"score_gpt":0.344974517411349,"score_spread":0.211389871784258,"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."}}