{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008035919,0.0008762605,0.0006607528,0.0005107645,0.0003185469,0.0007491473,0.001845414,0.0007860943,0.005357716],"category_scores_gemma":[0.002942004,0.0003649738,0.0005758162,0.0005775812,0.000446503,0.001751639,0.0009915857,0.001305323,0.002201616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000792521,"about_ca_system_score_gemma":0.001128691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008576212,"about_ca_topic_score_gemma":0.01606498,"domain_scores_codex":[0.9996069,0.00008242875,0.00002632828,0.000132096,0.00008891644,0.00006341598],"domain_scores_gemma":[0.9994537,0.0001671782,0.00003067431,0.0001736396,0.0001498711,0.0000249017],"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":[0.0003357317,0.0001424501,0.00175961,0.0001678349,0.0001197722,0.0002180452,0.0001743197,0.3104348,0.02390558,0.01664855,0.01847278,0.6276205],"study_design_scores_gemma":[0.00001242142,0.00003674273,0.0001612374,0.00000719194,0.00001315712,0.00003418502,0.00001693679,0.9837614,0.009986958,0.003304545,0.002656134,0.00000913863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07368549,0.0009138156,0.8983482,0.000550234,0.0003546109,0.0001089031,0.000415814,0.01641578,0.009207224],"genre_scores_gemma":[0.6020584,0.0003593215,0.3812363,0.000437781,0.0001212874,0.000226253,0.001723566,0.001005112,0.012832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008576212,"threshold_uncertainty_score":0.01792336,"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."}}