{"id":"W2756399388","doi":"10.6028/jres.125.003","title":"Performance of Test Supermartingale Confidence Intervals for the Success Probability of Bernoulli Trials","year":2020,"lang":"en","type":"article","venue":"Journal of Research of the National Institute of Standards and Technology","topic":"Quantum Mechanics and Applications","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Information Technology Laboratory; Natural Sciences and Engineering Research Council of Canada; Industry Canada","keywords":"Test (biology); Bell test experiments; Confidence interval; Quantum nonlocality; Bernoulli trial; Sequence (biology); Quantum entanglement; Statistical hypothesis testing; Bernoulli's principle","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004932958,0.00005522576,0.0003484151,0.0001075854,0.0001059067,0.000007540493,0.0005064236,0.00004262256,0.00002199087],"category_scores_gemma":[0.002730183,0.00003121147,0.0001233575,0.0004104177,0.0007635031,0.0001016041,0.000139543,0.0002403302,3.942434e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001996552,"about_ca_system_score_gemma":0.0005966878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001855258,"about_ca_topic_score_gemma":0.000002850781,"domain_scores_codex":[0.998378,0.0000506584,0.0007389285,0.00007883357,0.0006583669,0.00009522111],"domain_scores_gemma":[0.9944917,0.0007957561,0.0007668032,0.0001098665,0.003809295,0.00002658486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003113306,0.0002612525,0.02064894,0.0003898982,0.0002210093,8.127546e-8,0.0001518678,0.0001572913,0.08522677,0.8833533,0.0009172142,0.008361061],"study_design_scores_gemma":[0.001643048,0.001542014,0.002186631,0.0005037364,0.00007981579,0.000004675701,0.0004575839,0.005824034,0.6315143,0.3452645,0.01089672,0.00008303443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813629,0.0002361893,0.004354553,0.01254931,0.00005145044,0.0004591327,0.0008432215,0.000001659797,0.0001415242],"genre_scores_gemma":[0.9992756,0.00008561725,0.0005519743,0.000005575037,0.00005639263,0.00001417827,9.642091e-7,0.000003035231,0.000006640708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5462875,"threshold_uncertainty_score":0.3268481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1307715909407411,"score_gpt":0.4258003066846521,"score_spread":0.295028715743911,"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."}}