{"id":"W4389524555","doi":"10.18653/v1/2023.findings-emnlp.936","title":"RWKV: Reinventing RNNs for the Transformer Era","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":303,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"STELLA (programming language); Zhàng; Art history; Art; Humanities; Philosophy; History; Archaeology; China","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":[0.002719742,0.002035334,0.0009737381,0.001534136,0.0007548918,0.002301592,0.003705812,0.001956325,0.0210024],"category_scores_gemma":[0.009341056,0.001338088,0.00128415,0.0008499018,0.0007677916,0.008092727,0.003730047,0.003643585,0.01828944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008235325,"about_ca_system_score_gemma":0.001461307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009399713,"about_ca_topic_score_gemma":0.02041159,"domain_scores_codex":[0.9985834,0.0003862891,0.0001075352,0.0004641054,0.0003304528,0.0001282166],"domain_scores_gemma":[0.9976357,0.001128383,0.0000882548,0.0006332645,0.0004192966,0.00009504065],"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":[0.001066195,0.0001990066,0.001170723,0.0006762093,0.0003245737,0.0004271955,0.0003294883,0.04510872,0.01474764,0.01746338,0.1546223,0.7638646],"study_design_scores_gemma":[0.0002408531,0.0001970972,0.0003111641,0.0001536528,0.0001233304,0.0002384144,0.0001138912,0.8455394,0.02231022,0.03894074,0.09174083,0.00009045861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008089595,0.001755177,0.7423385,0.0007742451,0.001635239,0.0001469416,0.002678652,0.2345413,0.008040421],"genre_scores_gemma":[0.1876192,0.001865701,0.7183748,0.001720047,0.0006159995,0.0004378697,0.01708749,0.03780759,0.03447128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0210024,"threshold_uncertainty_score":0.07026005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02679878535284542,"score_gpt":0.3004265835493182,"score_spread":0.2736277981964728,"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."}}