{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001139935,0.0001923854,0.0002631714,0.0001978755,0.0005564573,0.00005365978,0.0006414212,0.00007248984,0.00001325501],"category_scores_gemma":[0.001135749,0.0002131739,0.00007092976,0.0006379901,0.0000340629,0.0001637877,0.00009719667,0.000988218,6.318463e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005145653,"about_ca_system_score_gemma":0.0000278529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002724339,"about_ca_topic_score_gemma":0.000001014317,"domain_scores_codex":[0.9983522,0.0003962645,0.0002147947,0.0004413713,0.0001692098,0.0004261029],"domain_scores_gemma":[0.9966026,0.002753817,0.00006471489,0.0004461102,0.00002896296,0.0001038091],"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":[0.000005277064,0.00001018206,0.0001434362,0.000005663767,0.00001630712,0.00001109667,0.0006300274,0.6088197,0.00003030023,0.0002649167,0.000001036624,0.390062],"study_design_scores_gemma":[0.0003148869,0.0003066419,0.0007965143,0.00001048605,0.00002237314,0.000354956,0.0002050997,0.9963505,0.00001495596,0.0003206688,0.001042149,0.0002607176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01210731,0.000103365,0.9852082,0.000206607,0.001291648,0.000126424,0.000001294383,0.0009487499,0.000006454764],"genre_scores_gemma":[0.3649241,0.000001849447,0.6347962,0.0001026654,0.00005178577,0.00007553241,0.000001859875,0.00002047658,0.00002553228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3898013,"threshold_uncertainty_score":0.8692977,"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."}}