{"id":"W3103682594","doi":"10.48550/arxiv.2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":195,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Transformer; Range (aeronautics); Computer science; Engineering; Electrical engineering; Geography; Cartography; Aerospace engineering; Voltage","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":[0.0001066826,0.0003411885,0.0003513164,0.0001422146,0.000236517,0.00007417327,0.001816864,0.0001948842,0.00001116166],"category_scores_gemma":[0.00001991898,0.0003999504,0.0003484634,0.0007903604,0.00009939152,0.0001774747,0.0007790424,0.0004630616,0.00004325327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001930074,"about_ca_system_score_gemma":0.000138576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001179096,"about_ca_topic_score_gemma":0.00002108621,"domain_scores_codex":[0.9977865,0.00004779462,0.0002224537,0.001396682,0.00009743604,0.0004491783],"domain_scores_gemma":[0.9983481,0.0002046907,0.0002021808,0.0008631338,0.0001236204,0.0002583068],"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":[0.00006926525,0.0001048983,0.000267752,0.00016036,0.00008568692,0.00009812413,0.0003143364,0.8157014,0.00005435526,0.1787675,0.0008220889,0.003554282],"study_design_scores_gemma":[0.0006942709,0.00006127933,0.0004968713,0.00005759981,0.00007916542,0.000003225539,0.00002523643,0.959959,0.0001490649,0.03554657,0.00240408,0.0005236689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02322847,0.00008663487,0.9727205,0.0008930168,0.0003742624,0.001242626,0.00005086977,0.0003595006,0.001044106],"genre_scores_gemma":[0.9899383,0.0001106996,0.009239902,0.0002442526,0.0001123631,0.00001960207,0.0000441897,0.0000257416,0.0002649472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9667099,"threshold_uncertainty_score":0.9998453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0710414840204032,"score_gpt":0.2081560915259502,"score_spread":0.137114607505547,"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."}}