{"id":"W4389524452","doi":"10.18653/v1/2023.emnlp-main.12","title":"Sparse Universal Transformer","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Transformer; Computer science; Inference; Computation; Scaling; Language model; Generalization; Theoretical computer science; Artificial intelligence; Algorithm; Computer engineering; 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":[0.001414408,0.001046105,0.001164978,0.0008804497,0.0006714589,0.001476933,0.002337472,0.001090522,0.01021482],"category_scores_gemma":[0.007172453,0.0006513874,0.00184622,0.0009337549,0.001597515,0.005629379,0.00344505,0.002048762,0.002736977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0010382,"about_ca_system_score_gemma":0.002223594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002981127,"about_ca_topic_score_gemma":0.005420847,"domain_scores_codex":[0.9987758,0.0002839091,0.00008346786,0.0003572165,0.0003460471,0.0001535761],"domain_scores_gemma":[0.9980091,0.0007607908,0.0001191651,0.0007233421,0.0002940024,0.00009351468],"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":[0.0004193666,0.0001543677,0.002021079,0.0005158834,0.0002032141,0.0004417035,0.0003798557,0.2243686,0.01609493,0.3137631,0.0235214,0.4181166],"study_design_scores_gemma":[0.00003358864,0.00007500176,0.0001767682,0.0000285933,0.00005165646,0.0002525308,0.00004916709,0.774319,0.006525768,0.2090951,0.009368106,0.00002470825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008034252,0.0002003802,0.9827321,0.0002524715,0.00006419983,0.00009618052,0.0004373259,0.003468373,0.004714685],"genre_scores_gemma":[0.4987158,0.0005965559,0.4844229,0.0007692734,0.0001561627,0.0003710072,0.002527795,0.001257131,0.01118331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01021482,"threshold_uncertainty_score":0.03417194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03619836200111303,"score_gpt":0.2409397845633939,"score_spread":0.2047414225622809,"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."}}