{"id":"W2019630194","doi":"10.1088/1367-2630/16/10/103032","title":"Randomized benchmarking with confidence","year":2014,"lang":"en","type":"article","venue":"New Journal of Physics","topic":"Quantum Information and Cryptography","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Army Research Office; Australian Research Council; Intelligence Advanced Research Projects Activity","keywords":"Benchmarking; Physics; Noise (video); Algorithm; Statistical physics; Variance (accounting); Computer science; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005574852,0.00007140153,0.0002397774,0.00005764542,0.00004617303,0.0001217189,0.0004193799,0.0000161296,0.0000103805],"category_scores_gemma":[0.00002910698,0.0000464267,0.0001239637,0.0002356629,0.00004666045,0.0008326228,0.00002408485,0.0001257262,0.000009013444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000601026,"about_ca_system_score_gemma":0.00008817846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004005437,"about_ca_topic_score_gemma":4.201161e-7,"domain_scores_codex":[0.9991665,0.00006771657,0.000277783,0.00005363181,0.0003319625,0.0001023299],"domain_scores_gemma":[0.9989677,0.0001646934,0.0004387691,0.0001536863,0.0001771587,0.00009801447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007316559,0.00001410881,0.00004112051,0.000005298755,0.00003173606,0.00000166009,0.0007878025,0.0003780877,0.00006967693,0.9232677,0.001631815,0.07303941],"study_design_scores_gemma":[0.2083606,0.000866788,0.0003895338,0.0003689383,0.00008638029,0.0002893613,0.0001022257,0.1720452,0.008720764,0.5811767,0.02708144,0.00051204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005232504,0.00004626852,0.9899029,0.0003416317,0.0002060526,0.00003981693,4.641857e-8,0.00001363962,0.004217216],"genre_scores_gemma":[0.94943,0.00003985957,0.04942732,0.0006966608,0.0003841602,4.706831e-7,1.500545e-7,0.000003313268,0.00001808846],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9441975,"threshold_uncertainty_score":0.1893226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01093744943337269,"score_gpt":0.2264678947918698,"score_spread":0.2155304453584971,"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."}}