{"id":"W4387947420","doi":"10.48550/arxiv.2310.15719","title":"Recurrent Linear Transformers","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; University of Alberta; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Inference; Computer science; Transformer; Leverage (statistics); Architecture; Reinforcement learning; Artificial intelligence; Machine learning; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007634693,0.000406519,0.0005469617,0.0003650062,0.0008873226,0.000009142481,0.0007807252,0.001096733,0.0008124789],"category_scores_gemma":[0.0002459194,0.000463363,0.0003221527,0.0006677276,0.0001788572,0.0001211771,0.0007448157,0.003403614,0.007308591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000868007,"about_ca_system_score_gemma":0.001100839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004860307,"about_ca_topic_score_gemma":0.007392019,"domain_scores_codex":[0.9963423,0.0006755479,0.0006936354,0.001164784,0.0001478994,0.0009758539],"domain_scores_gemma":[0.9971983,0.0007042226,0.0004048631,0.0008527776,0.0004347372,0.0004051236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002274361,0.000685307,0.4286022,0.01383249,0.0009942856,0.002318173,0.03389482,0.2359304,0.00007807783,0.2091491,0.05341089,0.01882987],"study_design_scores_gemma":[0.0009955349,0.0004479805,0.006827896,0.00525818,0.0005408154,0.000001891078,0.03871858,0.7056569,0.0001645844,0.1772132,0.06139252,0.002781883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9416568,0.0001576026,0.02752228,0.002169638,0.01227949,0.003308161,0.0004440846,0.001567064,0.0108949],"genre_scores_gemma":[0.9832677,0.001562844,0.00008711936,0.000295525,0.0006753915,0.00001555696,0.0001485134,0.00009718008,0.01385012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4697266,"threshold_uncertainty_score":0.9997818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4979293358280025,"score_gpt":0.3854878896133808,"score_spread":0.1124414462146217,"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."}}