{"id":"W3206410302","doi":"10.1002/spe.3036","title":"Transcoding Billions of Unicode Characters per Second with SIMD Instructions","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transcoding; Computer science; SIMD; Unicode; Software; Operating system; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00004802328,0.0000977008,0.0001312954,0.0001105792,0.0001556925,0.00003533114,0.0004283226,0.00004378764,0.0000944428],"category_scores_gemma":[0.000004343558,0.00009174048,0.00006076202,0.0006970805,0.00007294714,0.0008054159,0.00014959,0.0001202002,0.00001104931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002851359,"about_ca_system_score_gemma":0.0001108135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002249626,"about_ca_topic_score_gemma":0.00006740492,"domain_scores_codex":[0.999264,0.00004344179,0.00009694263,0.0003766492,0.00005839318,0.0001605947],"domain_scores_gemma":[0.9991454,0.00004424688,0.0000684802,0.00053809,0.0001136583,0.00009010841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007131937,0.0004960353,0.009628048,0.00009965977,0.0002485657,0.0005964423,0.001789682,0.02973549,0.03549766,0.9142744,0.0004951101,0.00706759],"study_design_scores_gemma":[0.006495226,0.0006858715,0.06077158,0.0005232253,0.0002782018,0.0004315508,0.003109237,0.7986959,0.05936243,0.01714933,0.05039139,0.002106091],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5388342,0.00001531747,0.4594725,0.00008942382,0.0001189445,0.00004221525,0.00001921551,0.00004971894,0.001358422],"genre_scores_gemma":[0.9932853,0.00004261092,0.005712759,0.00004812337,0.00001519388,1.647557e-7,0.000009828229,0.000005562566,0.0008804621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8971251,"threshold_uncertainty_score":0.3741068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04550440571683195,"score_gpt":0.160681029227551,"score_spread":0.1151766235107191,"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."}}