{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001041392,0.0001174923,0.0001543738,0.0002361919,0.00009293098,0.0001243263,0.000403852,0.00008709136,0.000002288032],"category_scores_gemma":[0.001192179,0.0001197055,0.00002347069,0.000310379,0.00001494904,0.0002703724,0.00002908226,0.0003354367,0.000003034169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002591252,"about_ca_system_score_gemma":0.00002295758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002128797,"about_ca_topic_score_gemma":0.000005336532,"domain_scores_codex":[0.9989451,0.0001395144,0.000190702,0.0004607583,0.00006982564,0.0001941149],"domain_scores_gemma":[0.997949,0.001433821,0.00002627827,0.0005209596,0.00002404137,0.00004592169],"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":[0.000006235698,0.00001798493,0.0004063612,0.0001503203,0.00001691829,0.000003638473,0.0006545256,0.03030114,0.00008313989,0.001164927,0.000005060024,0.9671897],"study_design_scores_gemma":[0.0001312086,0.00007110063,0.001342058,0.00008102266,0.00001569299,0.00002659609,0.00003034019,0.9670115,0.00005035923,0.0003266452,0.03077767,0.0001358528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001501083,0.0003290258,0.9965395,0.0003565793,0.0005388591,0.0001316402,0.000006800788,0.0005949118,0.000001595419],"genre_scores_gemma":[0.2088437,0.0001601909,0.790615,0.0000451788,0.00003918189,0.00005664349,0.0001685243,0.00001994589,0.00005158802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9670539,"threshold_uncertainty_score":0.488145,"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."}}