{"id":"W4398857059","doi":"10.7910/dvn/suv8dk","title":"Replication Data for: Assessing the Validity of Prevalence Estimates in Double List Experiments","year":2023,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Replication (statistics); Computer science; Statistics; Psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0278218,0.002440904,0.002089214,0.002421894,0.002591048,0.003044514,0.005030816,0.003603066,0.1849276],"category_scores_gemma":[0.1883865,0.001420371,0.002557125,0.004295786,0.001695372,0.001764768,0.002458567,0.00384502,0.07885291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001779529,"about_ca_system_score_gemma":0.005286233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009118983,"about_ca_topic_score_gemma":0.02067683,"domain_scores_codex":[0.9841979,0.006615479,0.002779215,0.003142123,0.002565345,0.0006999573],"domain_scores_gemma":[0.8717507,0.06211578,0.005936788,0.0462569,0.01230551,0.001634288],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0005084194,0.0001441939,0.002355047,0.001464441,0.0002240711,0.00007574632,0.0001212567,0.0005078614,0.0002858083,0.002328955,0.9858159,0.006168324],"study_design_scores_gemma":[0.01274422,0.0003280652,0.01951591,0.00145988,0.0009526831,0.0004470678,0.0002174423,0.001817267,0.002211299,0.02796257,0.9320542,0.0002893316],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001755426,0.0001562452,0.006213385,0.0004530493,0.0003010363,0.001606116,0.9850445,0.001397323,0.003072825],"genre_scores_gemma":[0.01445812,0.0001446187,0.02670124,0.001270728,0.0001679751,0.03073157,0.9140877,0.002382612,0.01005549],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9721782,"threshold_uncertainty_score":0.6186443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3021980780227468,"score_gpt":0.4833580003138783,"score_spread":0.1811599222911315,"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."}}