{"id":"W4413308446","doi":"10.1007/s10664-025-10707-0","title":"Towards understanding the challenges of bug localization in deep learning systems","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Deep learning; Data science; Artificial intelligence; Software 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":[0.006713052,0.0009014523,0.001196346,0.001778312,0.0008003928,0.005030428,0.002130404,0.002966237,0.002487596],"category_scores_gemma":[0.06177506,0.0009890986,0.0006377535,0.001243131,0.002699748,0.01264092,0.004164882,0.00580579,0.0004492895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001855976,"about_ca_system_score_gemma":0.002961522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008028561,"about_ca_topic_score_gemma":0.008116927,"domain_scores_codex":[0.9964162,0.001541925,0.000223763,0.0006759693,0.0007522824,0.0003898792],"domain_scores_gemma":[0.9533638,0.03423564,0.003710745,0.003877431,0.003957347,0.0008549324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003445415,0.0004526212,0.04120562,0.000695244,0.0002325084,0.0002881396,0.001688874,0.4167075,0.004926101,0.23346,0.008548412,0.2914504],"study_design_scores_gemma":[0.000008369932,0.00002564951,0.001119904,0.00005870352,0.00001414218,0.00003525833,0.000201933,0.7735333,0.0008193106,0.2229086,0.001262754,0.00001198856],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.116404,0.002497521,0.8649946,0.01140484,0.0001266071,0.00007291309,0.0003342245,0.000788277,0.003377018],"genre_scores_gemma":[0.8709539,0.001175807,0.1240765,0.0007706493,0.0001926187,0.0000641817,0.0003710143,0.0001856676,0.002209571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008028561,"threshold_uncertainty_score":0.03550243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04201334118444038,"score_gpt":0.2910416336842223,"score_spread":0.2490282924997819,"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."}}