{"id":"W3045102472","doi":"10.1088/2632-2153/abec21","title":"GPU coprocessors as a service for deep learning inference in high energy physics","year":2021,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Strong; High Energy Physics; U.S. Department of Energy; Office of Science; National Science Foundation","keywords":"Large Hadron Collider; Coprocessor; Workflow; Deep learning; Inference; Graphics; Energy (signal processing); Collider; High energy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001050652,0.0008192324,0.0005375983,0.0007982031,0.0006131185,0.002029592,0.002698263,0.0008342965,0.01493972],"category_scores_gemma":[0.003362019,0.0005271449,0.0005579187,0.001620102,0.000817,0.001525313,0.00178971,0.002654897,0.004471905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00136579,"about_ca_system_score_gemma":0.001606672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005813951,"about_ca_topic_score_gemma":0.007176277,"domain_scores_codex":[0.9992033,0.0001716843,0.00003504169,0.0001404834,0.000349449,0.0001000689],"domain_scores_gemma":[0.9982556,0.0003885831,0.00009245216,0.0005547823,0.0005017325,0.0002069467],"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":[0.002538331,0.0008339119,0.01221282,0.0005233654,0.0004081157,0.0007945167,0.0007211674,0.1750002,0.06256322,0.09300852,0.1659392,0.4854566],"study_design_scores_gemma":[0.0001107519,0.0001249782,0.001034732,0.00005594267,0.00003167632,0.0000908766,0.00006978165,0.9059445,0.02829432,0.02003615,0.04416766,0.0000386946],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07488333,0.001490903,0.8374428,0.001562188,0.0006035259,0.0002128539,0.0008167317,0.06040583,0.02258186],"genre_scores_gemma":[0.5029225,0.0008005942,0.4742849,0.0008865468,0.0001292564,0.0002167076,0.002029589,0.004369672,0.01436009],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01493972,"threshold_uncertainty_score":0.04997838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008290392874795395,"score_gpt":0.2632049768871998,"score_spread":0.2549145840124045,"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."}}