{"id":"W2978190445","doi":"10.1109/qrs.2019.00059","title":"TFCheck : A TensorFlow Library for Detecting Training Issues in Neural Network Programs","year":2019,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Implementation; Machine learning; Artificial intelligence; Training set; Artificial neural network; Code (set theory); Training (meteorology); Process (computing); Focus (optics); Software; 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":[0.001070149,0.0004198405,0.0005606539,0.0003760002,0.0002524686,0.0005927969,0.00159831,0.0003032209,0.00001955033],"category_scores_gemma":[0.0003123352,0.0004348263,0.0002239645,0.001278813,0.00005258179,0.001735024,0.000684123,0.0008325135,0.00001216275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001691364,"about_ca_system_score_gemma":0.0001899701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008278233,"about_ca_topic_score_gemma":0.0004089213,"domain_scores_codex":[0.9965554,0.0002494657,0.0006134073,0.0008576742,0.0003492562,0.00137479],"domain_scores_gemma":[0.9980115,0.0003986543,0.0003037943,0.001011113,0.00005598561,0.0002189088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001234827,0.0001123984,0.185314,0.00008948833,0.00003828663,0.00007365707,0.002428397,0.3137233,0.0007985784,0.03017128,0.0004458938,0.4666812],"study_design_scores_gemma":[0.0007445816,0.0002559747,0.01094709,0.0001402371,0.000008328277,0.00005769741,0.0002173169,0.9787841,0.0003984924,0.004860251,0.003082467,0.0005034392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2203724,0.0008525846,0.7697195,0.004404285,0.0004608015,0.001788125,0.000003024886,0.002063376,0.0003359483],"genre_scores_gemma":[0.5633028,0.00001136999,0.4346831,0.0008281383,0.0002859807,0.0003897203,0.00001008978,0.00007172803,0.0004169966],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6650608,"threshold_uncertainty_score":0.9998103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01657572878440712,"score_gpt":0.2478104125994643,"score_spread":0.2312346838150572,"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."}}