{"id":"W4280562623","doi":"10.1145/3529318","title":"Testing Feedforward Neural Networks Training Programs","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Debugging; Hyperparameter; Artificial neural network; Machine learning; Artificial intelligence; Software; Deep neural networks; Training (meteorology); Deep learning; Test data; Software engineering; Programming language","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":[0.002495747,0.001118288,0.0003660788,0.0005617309,0.0002889341,0.0005518908,0.001866024,0.0009599824,0.004197607],"category_scores_gemma":[0.02015126,0.0004447394,0.0005449057,0.0003334676,0.001018079,0.001537323,0.0007865357,0.001041575,0.0006368725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001373966,"about_ca_system_score_gemma":0.001274179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005257924,"about_ca_topic_score_gemma":0.00617167,"domain_scores_codex":[0.998387,0.0004832307,0.000133609,0.0004345528,0.0003903679,0.0001712312],"domain_scores_gemma":[0.9854833,0.01027635,0.0007485861,0.001623878,0.00169884,0.0001690707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006553139,0.0004177682,0.01816207,0.0005268664,0.0001098427,0.0003860383,0.0002558824,0.7647144,0.02034059,0.005626909,0.004996429,0.1838079],"study_design_scores_gemma":[0.00002899375,0.0001202529,0.0007253119,0.0000314931,0.00001186685,0.0000315047,0.00002409142,0.977572,0.01879242,0.002025175,0.0006288178,0.000008080959],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6682219,0.0003679785,0.3031165,0.0007074854,0.0001876231,0.0001978285,0.001177259,0.02086817,0.00515529],"genre_scores_gemma":[0.9013596,0.00009857047,0.09498481,0.0002094924,0.00001379685,0.0001695421,0.001224618,0.0005073879,0.00143228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005257924,"threshold_uncertainty_score":0.01404238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1199166601035608,"score_gpt":0.3055727679422794,"score_spread":0.1856561078387187,"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."}}