{"id":"W2972233065","doi":"10.1109/qrs.2019.00059","title":"TFCheck : A TensorFlow Library for Detecting Training Issues in Neural Network Programs","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Implementation; Machine learning; Code (set theory); Training set; Artificial intelligence; Training (meteorology); Process (computing); Artificial neural network; Focus (optics); Software engineering; Data mining; Programming language; Set (abstract data type)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008539571,0.0004981699,0.000743871,0.0002083906,0.0001542576,0.0008633325,0.002364524,0.0004510345,0.00001991281],"category_scores_gemma":[0.0002844132,0.0004780417,0.000279532,0.0005065769,0.00004165195,0.0008491899,0.00359192,0.001659809,0.00001181125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005826678,"about_ca_system_score_gemma":0.0002346166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008299792,"about_ca_topic_score_gemma":0.00003173298,"domain_scores_codex":[0.9965085,0.0002527274,0.0006422462,0.001296991,0.000323302,0.0009762521],"domain_scores_gemma":[0.9978825,0.0005218982,0.0003763501,0.001060366,0.000051674,0.000107209],"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":[0.00002015256,0.00002070176,0.007552735,0.0001624585,0.00002693166,0.00001750739,0.002375598,0.7241629,0.000003569394,0.002113197,0.0002645529,0.2632796],"study_design_scores_gemma":[0.0004412757,0.00009925985,0.0007775783,0.0003819308,0.00001054498,0.000009144009,0.0002203802,0.9869022,0.00001694082,0.00760476,0.002965034,0.0005708879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02287636,0.0006268298,0.9640702,0.002589782,0.003370352,0.002186534,0.000002005933,0.001738493,0.002539433],"genre_scores_gemma":[0.4259939,0.000007884315,0.571178,0.0002810647,0.001039223,0.0001934739,0.00002699851,0.00007642677,0.001203121],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4031175,"threshold_uncertainty_score":0.9997671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04738158154081169,"score_gpt":0.2962145034165068,"score_spread":0.2488329218756952,"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."}}