{"id":"W3085652395","doi":"10.1145/3393673.3276968","title":"Numerical computing on the web: benchmarking for the future","year":2020,"lang":"en","type":"article","venue":"ACM SIGPLAN Notices","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Benchmarking; Computer science; JavaScript; Benchmark (surveying); Suite; Web application; Workstation; Mobile device; Operating system; Unobtrusive JavaScript; World Wide Web; Rich Internet application","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":[0.01152205,0.001142461,0.001070409,0.00231735,0.0009680078,0.004933259,0.003411025,0.001217302,0.002037255],"category_scores_gemma":[0.02456964,0.0004807871,0.0007014444,0.006196451,0.001383958,0.006329474,0.002410023,0.002748167,0.001366472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002078626,"about_ca_system_score_gemma":0.002784441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008670414,"about_ca_topic_score_gemma":0.006066883,"domain_scores_codex":[0.9872684,0.003688596,0.0007802493,0.0009956697,0.006259243,0.001007848],"domain_scores_gemma":[0.9814897,0.004445678,0.0008208575,0.00561324,0.006289772,0.001340679],"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":[0.001964858,0.001962366,0.03475115,0.001218829,0.0004029238,0.0003406054,0.0008340977,0.2422594,0.02186863,0.06492284,0.08214524,0.5473291],"study_design_scores_gemma":[0.0001302902,0.0004918777,0.01368567,0.0004205289,0.0001037359,0.0002249479,0.0007674987,0.8566854,0.0283841,0.03763806,0.06133088,0.0001371234],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5068516,0.02090212,0.3281094,0.01393326,0.001866226,0.0004799163,0.003937051,0.04142832,0.08249211],"genre_scores_gemma":[0.7876521,0.005369972,0.1901266,0.0009515563,0.0003015183,0.0003004554,0.007417032,0.004417527,0.003463196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01152205,"threshold_uncertainty_score":0.0609352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02884036809374038,"score_gpt":0.2460933629192955,"score_spread":0.2172529948255551,"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."}}