{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004590954,0.0002434228,0.0003041142,0.0001736,0.0002746172,0.00004476778,0.0008436788,0.00004701289,0.00001561134],"category_scores_gemma":[0.008893302,0.000254592,0.00007493827,0.002194335,0.0000162344,0.0001468617,0.001193398,0.0009437258,7.913206e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000225928,"about_ca_system_score_gemma":0.00004709311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001372187,"about_ca_topic_score_gemma":0.00001304631,"domain_scores_codex":[0.9981323,0.0001084108,0.0004250459,0.0005039689,0.0003712685,0.0004589528],"domain_scores_gemma":[0.9964635,0.002595755,0.0001648505,0.0004804652,0.0001284395,0.0001670125],"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":[0.000006570829,0.00004112218,0.0601319,0.00001037401,0.000009057035,0.00001628879,0.0002964257,0.904388,0.00008400979,0.000007437421,0.0002009518,0.03480794],"study_design_scores_gemma":[0.0001621095,0.0002225099,0.02819496,0.00002574211,0.000006162208,0.00007903717,0.00002777124,0.9703556,0.00004089443,0.00001292276,0.0006182452,0.0002541066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09758713,0.00006394512,0.898588,0.0002882823,0.002405311,0.0001480759,0.000004598066,0.0008967158,0.00001796549],"genre_scores_gemma":[0.7462247,1.309802e-7,0.2530994,0.0002949463,0.000276024,0.00002016468,0.00001047805,0.00003623799,0.0000379697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6486376,"threshold_uncertainty_score":0.9999906,"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."}}