{"id":"W4402661245","doi":"10.1109/tse.2024.3461657","title":"D<sup>3</sup>: Differential Testing of Distributed Deep Learning With Model Generation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Division of Computing and Communication Foundations","keywords":"Computer science; Artificial intelligence; Programming language","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":[0.0001215492,0.0002314669,0.0002012294,0.0002494741,0.000177237,0.0001478428,0.0002883112,0.00008793383,0.00001138126],"category_scores_gemma":[0.00007008613,0.0002213683,0.00008017183,0.000733219,0.00002188853,0.0005115815,0.000006426994,0.0006532473,0.000005706796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001208,"about_ca_system_score_gemma":0.00005770419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001152563,"about_ca_topic_score_gemma":0.000001473561,"domain_scores_codex":[0.9987049,0.0000341219,0.0002580544,0.0004033083,0.0003233165,0.0002763375],"domain_scores_gemma":[0.9992386,0.0002957774,0.00004556109,0.0002635784,0.00008110652,0.00007543873],"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":[0.000004934957,0.00002123825,0.00003380969,0.00007081337,0.00004837453,0.00001180505,0.0004788477,0.9726385,0.001585356,0.0002865603,0.000002195312,0.02481749],"study_design_scores_gemma":[0.0001821153,0.00008581462,0.00003087769,0.0001584078,0.00003590207,0.00002133622,0.00001213126,0.9947996,0.004409287,0.00001037035,0.00002415154,0.0002299728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0438026,0.00004322062,0.9544497,0.00001641371,0.0003161281,0.0001051306,0.000008481061,0.001251925,0.000006425286],"genre_scores_gemma":[0.7221721,0.000002713999,0.2776644,0.000003323501,0.00006554244,0.00001975459,0.000006218027,0.00003418205,0.00003173492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6783695,"threshold_uncertainty_score":0.9027138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0148244596035767,"score_gpt":0.2191913172321724,"score_spread":0.2043668576285957,"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."}}