{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05342732,0.001256333,0.00214457,0.00458342,0.0008671779,0.004527647,0.003816121,0.002855308,0.004067603],"category_scores_gemma":[0.2521745,0.0007385334,0.001623683,0.002229612,0.003175883,0.004517236,0.003018692,0.003395962,0.0006094138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001908214,"about_ca_system_score_gemma":0.002278722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003446502,"about_ca_topic_score_gemma":0.001245684,"domain_scores_codex":[0.9775584,0.01212312,0.001362518,0.002384878,0.005527014,0.001044057],"domain_scores_gemma":[0.5834451,0.3788157,0.008931461,0.01687717,0.008925113,0.003005363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005500602,0.0002685357,0.02876025,0.0007345121,0.0008270275,0.0004857418,0.001011358,0.5752827,0.004650475,0.1869647,0.002245311,0.1932688],"study_design_scores_gemma":[0.00009685507,0.0003802593,0.003775416,0.0001193301,0.00006345172,0.0002321189,0.0001182029,0.9377737,0.007668833,0.04887489,0.0007871844,0.0001097884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1782808,0.002394023,0.8086467,0.0006706362,0.0001873953,0.0001557521,0.0004897431,0.002705366,0.006469463],"genre_scores_gemma":[0.8330716,0.0003994466,0.1644556,0.00015088,0.00007567614,0.0001391658,0.0006796563,0.0003281137,0.0006998216],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05342732,"threshold_uncertainty_score":0.2825541,"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."}}