{"id":"W4414021351","doi":"10.22331/q-2025-09-05-1848","title":"A Theory of Direct Randomized Benchmarking","year":2025,"lang":"en","type":"article","venue":"Quantum","topic":"Quantum Computing Algorithms and Architecture","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Office of Science; Office of the Director of National Intelligence; Advanced Scientific Computing Research; U.S. Department of Energy","keywords":"Benchmarking; Randomized controlled trial; Computer science; Business; Medicine; Internal medicine; Marketing","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":[0.01043652,0.001616429,0.002200666,0.002997341,0.003489617,0.0065179,0.005456513,0.004822304,0.02218668],"category_scores_gemma":[0.03773242,0.001097255,0.002561484,0.003167351,0.009394595,0.01222791,0.007337003,0.007449868,0.004309169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005082341,"about_ca_system_score_gemma":0.004656206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002856461,"about_ca_topic_score_gemma":0.001892449,"domain_scores_codex":[0.9855033,0.005596983,0.0007252794,0.002981397,0.003727344,0.001465715],"domain_scores_gemma":[0.9778904,0.01242375,0.001380777,0.004982781,0.002665168,0.0006570118],"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":[0.000009333969,0.000008371601,0.00005291332,0.00002225784,0.000007045341,0.00001453853,0.0000285409,0.002744178,0.00006249602,0.9926381,0.00151684,0.00289534],"study_design_scores_gemma":[0.0000153354,0.00001321631,0.00003124498,0.00002432447,0.000007244456,0.00003382908,0.00001109821,0.03312435,0.0001838341,0.9618334,0.004708884,0.00001322085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007853867,0.001599877,0.8616562,0.004438777,0.0007226498,0.0002406085,0.0005754888,0.0007219696,0.1221905],"genre_scores_gemma":[0.573055,0.003224361,0.3161094,0.007518985,0.00269275,0.00322989,0.001372095,0.001377543,0.09142001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02218668,"threshold_uncertainty_score":0.07422179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006763334639812611,"score_gpt":0.235311112894705,"score_spread":0.2285477782548924,"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."}}