{"id":"W3130765241","doi":"10.48550/arxiv.2102.11417","title":"Parallelizing Legendre Memory Unit Training","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Leverage (statistics); Recurrent neural network; Machine translation; Artificial intelligence; Inference; Benchmark (surveying); Transformer; Invariant (physics); Machine learning; Artificial neural network; Mathematics","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":[0.0003042374,0.0003393317,0.0004095155,0.0002337221,0.0001950475,0.0002595548,0.002278591,0.0003230291,0.00006282982],"category_scores_gemma":[0.00003429667,0.0004410454,0.0002649943,0.0004894969,0.00005898946,0.0005202498,0.003019175,0.0008662845,0.00004068216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001442181,"about_ca_system_score_gemma":0.0005130534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001260347,"about_ca_topic_score_gemma":0.00009050652,"domain_scores_codex":[0.9974964,0.0001840255,0.0002486195,0.001452515,0.0001313903,0.0004870619],"domain_scores_gemma":[0.9975998,0.00008678728,0.0002043364,0.001749808,0.0001548827,0.0002043717],"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":[0.000006253847,0.00005000662,0.0006569675,0.000115986,0.0001458244,0.002197955,0.003566375,0.7654698,0.00008552102,0.2203327,0.00007633114,0.007296271],"study_design_scores_gemma":[0.0004075107,0.00001588714,0.0002462883,0.0002131943,0.00005297938,0.00002448386,0.001815603,0.9838446,0.0001507136,0.01175695,0.0007909316,0.0006808479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2798442,0.0002061275,0.7121122,0.0001543895,0.0008378503,0.000130531,0.000002373378,0.0003154455,0.006396928],"genre_scores_gemma":[0.9814971,0.0001275407,0.01583468,0.0001852288,0.000151123,7.98986e-7,0.00001429034,0.00002206643,0.002167166],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7016529,"threshold_uncertainty_score":0.9998041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2028070691661144,"score_gpt":0.2042012480033702,"score_spread":0.001394178837255761,"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."}}