{"id":"W4396661957","doi":"10.1051/epjconf/202429507024","title":"HEPScore: A new CPU benchmark for the WLCG","year":2024,"lang":"en","type":"article","venue":"EPJ Web of Conferences","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Particle Physics; University of Victoria","funders":"","keywords":"Benchmark (surveying); National laboratory; Resource (disambiguation); Software; Procurement; Computer science; Operating system; Physics; Business","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":[0.004422525,0.001858841,0.000930876,0.002722217,0.0007933265,0.002371196,0.004080446,0.001006425,0.005899324],"category_scores_gemma":[0.009495081,0.0006324108,0.001006262,0.004504113,0.0006158418,0.003018337,0.002021359,0.002324019,0.003713981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002851228,"about_ca_system_score_gemma":0.003790582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0198351,"about_ca_topic_score_gemma":0.01664229,"domain_scores_codex":[0.9945102,0.0009061859,0.0004105213,0.000515433,0.003047449,0.0006101432],"domain_scores_gemma":[0.9941158,0.001005749,0.000329126,0.000877183,0.003110052,0.0005621697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001637638,0.0004310393,0.008589887,0.001515357,0.0002951525,0.0002461707,0.0001610581,0.08053625,0.01660125,0.02493506,0.7020009,0.1630503],"study_design_scores_gemma":[0.0006401888,0.000903705,0.01641433,0.0005361328,0.0002082533,0.0003982613,0.0001874216,0.2618549,0.03668355,0.01589598,0.6660197,0.0002574429],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2266338,0.03050742,0.2612623,0.006683499,0.007570763,0.0022819,0.1151491,0.1261677,0.2237435],"genre_scores_gemma":[0.3059072,0.005760868,0.2462916,0.002547841,0.001046871,0.001926598,0.3797388,0.02960331,0.02717689],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0198351,"threshold_uncertainty_score":0.03943926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03219257986751806,"score_gpt":0.29030002148987,"score_spread":0.2581074416223519,"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."}}