{"id":"W4289978463","doi":"10.1007/s10664-022-10172-z","title":"Correction to: Can Offline Testing of Deep Neural Networks Replace Their Online Testing?","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial neural network; Deep neural networks; Artificial intelligence; Online and offline; Machine learning; Information retrieval; Data mining; Data science; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005334527,0.001919651,0.002812692,0.002860935,0.00302302,0.004129187,0.004664567,0.01121464,0.128433],"category_scores_gemma":[0.1719273,0.001314785,0.001647886,0.002747004,0.00304559,0.003296504,0.002784527,0.01186145,0.0596079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00348728,"about_ca_system_score_gemma":0.005329015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008099953,"about_ca_topic_score_gemma":0.01021409,"domain_scores_codex":[0.9941571,0.0009158236,0.001067202,0.001171361,0.002023276,0.0006652762],"domain_scores_gemma":[0.8946709,0.03860052,0.004846582,0.009979479,0.04737844,0.004524175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007078413,0.00001234435,0.0001966074,0.00009852449,0.00002957661,0.0003241051,0.00005038982,0.0001511065,0.0001181132,0.002251815,0.9863573,0.01033933],"study_design_scores_gemma":[0.0002519807,0.00007787706,0.00296171,0.0005037548,0.0000919624,0.001626468,0.0002473451,0.003510011,0.001951224,0.01945711,0.9691386,0.0001819264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"editorial","genre_gemma":"empirical","genre_scores_codex":[0.0005262517,0.0005233037,0.003553434,0.1006591,0.8866194,0.00003434848,0.003258331,0.002085197,0.002740656],"genre_scores_gemma":[0.08993129,0.004460049,0.02305503,0.1849735,0.4852293,0.0005118367,0.008337678,0.005008125,0.1984932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.128433,"threshold_uncertainty_score":0.4296513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02439196730745248,"score_gpt":0.2589459812873127,"score_spread":0.2345540139798603,"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."}}