{"id":"W3044932337","doi":"10.1109/ispass48437.2020.00017","title":"SeqPoint: Identifying Representative Iterations of Sequence-Based Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"Advanced Micro Devices","keywords":"Computer science; Profiling (computer programming); Computation; Artificial neural network; Exploit; Convolutional neural network; Deep neural networks; Sequence (biology); Artificial intelligence; Recurrent neural network; Machine learning; Algorithm; Programming language","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":[0.0001357377,0.0003443408,0.0004504163,0.0001404923,0.0001719268,0.0002583149,0.001980837,0.000170244,0.00003227767],"category_scores_gemma":[0.00007172933,0.0003476843,0.0002500547,0.0008836272,0.0001457097,0.0004326784,0.002101748,0.0008434848,0.0000145507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007851992,"about_ca_system_score_gemma":0.0001500866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005161266,"about_ca_topic_score_gemma":0.00001923071,"domain_scores_codex":[0.9972072,0.0001812194,0.0007293586,0.001151277,0.0003950143,0.0003359121],"domain_scores_gemma":[0.9969164,0.0004066783,0.0006023452,0.001622141,0.0002767431,0.0001756766],"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":[0.000006372709,0.00003561364,0.0001251798,0.00005579693,0.00003304262,0.00001771081,0.0003457539,0.9459888,0.0009277923,0.04720839,0.001638887,0.003616708],"study_design_scores_gemma":[0.0001524538,0.00002580965,0.0001927376,0.00006143368,0.00001863898,0.00000473035,0.00001669073,0.9676294,0.002854719,0.028653,0.0001004186,0.0002899355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007241533,0.0001437388,0.99011,0.006282307,0.000498902,0.000796794,0.00002622952,0.0004812415,0.000936587],"genre_scores_gemma":[0.7369865,0.00002684929,0.2612758,0.001059741,0.0001816209,0.0002248489,0.0001151129,0.00002488729,0.0001046452],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7362624,"threshold_uncertainty_score":0.9998975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.111705551025448,"score_gpt":0.3580130596449512,"score_spread":0.2463075086195033,"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."}}