{"id":"W4412865071","doi":"10.1088/2058-9565/adf1c0","title":"Application-level benchmarking of quantum computers using nonlocal game strategies","year":2025,"lang":"en","type":"article","venue":"Quantum Science and Technology","topic":"Quantum Information and Cryptography","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Canadian Institute for Advanced Research","funders":"Pacific Northwest National Laboratory","keywords":"Computer science; Quantum; Benchmark (surveying); Hamiltonian (control theory); Quantum computer; Benchmarking; Task (project management); Graph; Theoretical computer science; Mathematical optimization; Algorithm; Mathematics; Physics; Quantum mechanics","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":[0.00300398,0.0004476281,0.0006475905,0.0006809952,0.0005820855,0.001118677,0.001857509,0.001037006,0.001588112],"category_scores_gemma":[0.01135397,0.000234411,0.0002813312,0.0007233405,0.001320904,0.001517389,0.001001722,0.001106054,0.0001576554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001458309,"about_ca_system_score_gemma":0.001184597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002626332,"about_ca_topic_score_gemma":0.002668648,"domain_scores_codex":[0.9976501,0.001026844,0.000112246,0.0003323939,0.0005926829,0.0002857482],"domain_scores_gemma":[0.9929004,0.004268035,0.0003824775,0.001297718,0.0008542841,0.0002972961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006798643,0.0009071039,0.008232551,0.0001917862,0.0001769269,0.0001700195,0.0002256834,0.8739161,0.02586043,0.05793656,0.0008340634,0.03086882],"study_design_scores_gemma":[0.00001774865,0.0001354234,0.0004835793,0.000002998749,0.000004538477,0.00001020992,0.00002118659,0.9876602,0.007520371,0.003978803,0.0001569226,0.000007962502],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9252331,0.00009374472,0.07072062,0.0001931458,0.00003192418,0.0001060493,0.000057311,0.0003294434,0.003234745],"genre_scores_gemma":[0.9896596,0.00001127328,0.01002851,0.00001577774,0.00000213495,0.00002517085,0.00002614618,0.000016916,0.000214511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00300398,"threshold_uncertainty_score":0.01588678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01435005018917165,"score_gpt":0.2727587242467185,"score_spread":0.2584086740575469,"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."}}