{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00261619,0.0002405291,0.0004609896,0.00008673211,0.0001045257,0.0001380468,0.00202912,0.0001699065,0.000599115],"category_scores_gemma":[0.01269426,0.0001823353,0.00004919542,0.0002124297,0.0001613408,0.0003315028,0.001095354,0.000259182,0.0008845056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005562996,"about_ca_system_score_gemma":0.0001304913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005029178,"about_ca_topic_score_gemma":0.00009203028,"domain_scores_codex":[0.9977746,0.0001922345,0.0006603855,0.0007507679,0.0003590071,0.0002629816],"domain_scores_gemma":[0.9889222,0.004548087,0.0005358646,0.005845513,0.0000971199,0.00005126536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002217961,0.0001157131,0.0000627991,0.001648877,0.00002529391,0.000005048588,0.00001875052,2.130089e-7,0.00004141186,0.004009639,0.9935253,0.0005247746],"study_design_scores_gemma":[0.0004450813,0.00002918004,0.0002425581,0.0007876982,0.0002315739,0.000002994911,0.00005846754,0.001470322,0.0003106564,0.04086167,0.9553284,0.0002313632],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00002314691,0.000001207218,0.0791496,0.0000076483,0.0002713696,0.0007362898,0.9197515,0.00003225725,0.00002702496],"genre_scores_gemma":[0.000006359865,0.0001113723,0.2138466,0.00001733231,0.00006667506,0.0001357046,0.7857587,0.00002205284,0.00003509875],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.134697,"threshold_uncertainty_score":0.9998934,"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."}}