{"id":"W3201160209","doi":"10.1002/spe.3036","title":"Transcoding billions of Unicode characters per second with SIMD instructions","year":2021,"lang":"en","type":"preprint","venue":"Software Practice and Experience","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"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":[0.0001727525,0.0002702434,0.0003454757,0.0001279919,0.0002849407,0.0004255215,0.0007504619,0.0001688132,0.00004886437],"category_scores_gemma":[0.0001974151,0.0002256754,0.0000709479,0.0002936689,0.0001950417,0.002795517,0.00103915,0.0006209214,0.000001921798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002958283,"about_ca_system_score_gemma":0.0003313735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001919773,"about_ca_topic_score_gemma":0.00003201201,"domain_scores_codex":[0.9980968,0.0001105234,0.0003374931,0.0008151375,0.0003767622,0.0002633443],"domain_scores_gemma":[0.9977928,0.0003457964,0.0003772271,0.00103741,0.0002976056,0.0001491541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004736601,0.002128013,0.006203844,0.002598257,0.001027437,0.0006673059,0.5188044,0.002329007,0.02298115,0.01648241,0.0009669632,0.4253376],"study_design_scores_gemma":[0.008504389,0.003355236,0.04100172,0.01444895,0.001487884,0.009945011,0.2472858,0.05629635,0.07641231,0.006385112,0.5209576,0.01391971],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2857112,0.00114292,0.7108637,0.0008317097,0.0007568922,0.0002453447,0.00005350498,0.0001507584,0.0002439231],"genre_scores_gemma":[0.5980129,0.001093213,0.4002485,0.0003558419,0.00006620223,0.00008092162,0.00004780596,0.00001995001,0.00007464164],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5199906,"threshold_uncertainty_score":0.9202775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01794266087902488,"score_gpt":0.2716954210409309,"score_spread":0.253752760161906,"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."}}