{"id":"W4294233607","doi":"10.15626/mp.2021.2720","title":"Z-curve 2.0: Estimating Replication Rates and Discovery Rates","year":2022,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Replication (statistics); Confidence interval; False discovery rate; Statistics; Selection (genetic algorithm); False positive paradox; Multiple comparisons problem; Computer science; Range (aeronautics); Extension (predicate logic); Statistical power; Econometrics; Mathematics; Artificial intelligence; Biology; Engineering","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007435662,0.0002077712,0.0008794412,0.00008822545,0.0002469225,0.00005371817,0.0003175724,0.00009464981,0.001365496],"category_scores_gemma":[0.06030139,0.0001702773,0.0001639292,0.000266899,0.0002123765,0.00009941067,0.0002914481,0.0004343012,0.00002245408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002315106,"about_ca_system_score_gemma":0.00002062444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008719313,"about_ca_topic_score_gemma":0.000001840573,"domain_scores_codex":[0.9951055,0.002602671,0.0009406981,0.0007995249,0.0002542006,0.0002974129],"domain_scores_gemma":[0.9731434,0.0252068,0.0004562248,0.001055938,0.00005755076,0.00008010906],"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":[0.0009231677,0.001814323,0.008078642,0.0003717468,0.004676923,0.0001154824,0.001116703,0.00007334703,0.009564796,0.7168034,0.102731,0.1537306],"study_design_scores_gemma":[0.0006487608,0.0002309523,0.002684729,0.000003819187,0.0007278182,0.00004508838,0.00002988985,0.0006837421,0.0003296986,0.9889766,0.005443143,0.0001957464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06307341,0.0007893696,0.9164829,0.01145749,0.002408108,0.001109586,0.000275743,0.0002459409,0.004157405],"genre_scores_gemma":[0.05193904,0.00002354443,0.9439685,0.002491086,0.0002230139,0.0005782188,0.00001088853,0.00004708385,0.0007186732],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2721733,"threshold_uncertainty_score":0.9995474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7276317683307449,"score_gpt":0.64387429511749,"score_spread":0.083757473213255,"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."}}