{"id":"W4285787112","doi":"10.48550/arxiv.1909.02562","title":"TFCheck : A TensorFlow Library for Detecting Training Issues in Neural\\n Network Programs","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Implementation; Machine learning; Code (set theory); Artificial intelligence; Process (computing); Training set; Artificial neural network; Training (meteorology); Focus (optics); Software engineering; 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":[0.0005330529,0.0004802879,0.0006495535,0.0003133573,0.000218011,0.0003540053,0.002568234,0.0004460592,0.0000122887],"category_scores_gemma":[0.0001612978,0.0005711986,0.0003181442,0.001052472,0.0000770916,0.001097745,0.002963363,0.001390255,0.00001734239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001306766,"about_ca_system_score_gemma":0.0002427856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007894676,"about_ca_topic_score_gemma":0.0000329579,"domain_scores_codex":[0.9967373,0.0003072249,0.0003606633,0.001608807,0.0001177326,0.0008682868],"domain_scores_gemma":[0.9977251,0.0004475072,0.0004358658,0.001177112,0.00007233128,0.0001420276],"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":[0.00005061451,0.0000338816,0.0175241,0.0001484934,0.00004593463,0.000159501,0.001003077,0.9527053,0.000003123071,0.01184195,0.00008975023,0.01639424],"study_design_scores_gemma":[0.000695646,0.0001000434,0.0008838365,0.0003739495,0.00003379392,0.000005185889,0.000278182,0.976683,0.00000868597,0.01907677,0.001256328,0.0006046272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1967877,0.0002550796,0.7978492,0.0003895715,0.001599479,0.001305705,0.000004199015,0.0009338971,0.0008751395],"genre_scores_gemma":[0.9390652,0.00004041406,0.05890223,0.0001183547,0.0004492139,0.000007718579,0.00002644714,0.00006980741,0.001320593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7422775,"threshold_uncertainty_score":0.999674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09169102174530505,"score_gpt":0.2195692954900726,"score_spread":0.1278782737447676,"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."}}