{"id":"W4402606258","doi":"10.22541/au.172665939.98271085/v1","title":"Scanning HTML at Tens of Gigabytes per Second on ARM Processors","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Computer science; ARM architecture; Parallel computing; Operating system","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":[0.0007705615,0.000950409,0.0006543809,0.001464897,0.0004445492,0.001796306,0.001087012,0.0008258338,0.02017736],"category_scores_gemma":[0.003991419,0.0006044887,0.0003701688,0.00237153,0.0002856661,0.001820044,0.0008126206,0.0006695917,0.01175198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004883913,"about_ca_system_score_gemma":0.0006302819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002332768,"about_ca_topic_score_gemma":0.002347829,"domain_scores_codex":[0.9988306,0.0001195976,0.00009851002,0.0002655472,0.0005556893,0.0001300604],"domain_scores_gemma":[0.9982469,0.0005131638,0.0001328692,0.0005073922,0.0005158377,0.00008371423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002003082,0.0002130023,0.00720528,0.0004860239,0.0001743877,0.0003654414,0.0003486015,0.01086632,0.08026566,0.008101528,0.1185303,0.7714404],"study_design_scores_gemma":[0.0004080698,0.0005522101,0.02164475,0.0003656143,0.0002211404,0.001221278,0.000592314,0.4392783,0.2355781,0.03044985,0.2694979,0.0001903873],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1748314,0.003654357,0.5379032,0.001577627,0.0005021486,0.0003615954,0.007527163,0.2007394,0.07290307],"genre_scores_gemma":[0.5468363,0.002052103,0.3997056,0.0007259449,0.0002058238,0.0003368191,0.009843325,0.003641105,0.03665304],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02017736,"threshold_uncertainty_score":0.0675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02248724263591914,"score_gpt":0.2658976587368829,"score_spread":0.2434104161009638,"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."}}