{"id":"W4398689099","doi":"10.7910/dvn/esthij","title":"Replication Data for: Hypothesis Testing with Error Correction Models","year":2021,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Replication (statistics); Computer science; Statistics; 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":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006583898,0.0003305029,0.0003514995,0.0001280492,0.0002403252,0.0004879564,0.00362136,0.0002251591,0.00009261881],"category_scores_gemma":[0.001496494,0.000308703,0.00004554747,0.0004452205,0.00004800837,0.00150489,0.001338592,0.0003440751,0.001366758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007707273,"about_ca_system_score_gemma":0.0005369175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004031872,"about_ca_topic_score_gemma":0.0002243648,"domain_scores_codex":[0.9970008,0.00008886411,0.0003649699,0.001800867,0.0003924393,0.0003520572],"domain_scores_gemma":[0.9879818,0.0005074747,0.0003591048,0.0106592,0.000362697,0.0001297104],"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":[0.00001336406,0.00005507301,5.867897e-7,0.00007087426,0.00003674237,0.00001400845,0.000009163884,0.0009609647,0.00001013734,0.00007936057,0.986211,0.01253874],"study_design_scores_gemma":[0.0001228402,0.00004510958,0.000001434737,0.0001638486,0.00006996562,0.00005034958,0.000009583806,0.3819676,0.00001861031,0.0003356694,0.6169604,0.0002546037],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[7.223313e-7,0.0000015,0.462146,0.00001356994,0.0003522901,0.00017601,0.5371714,0.00009855887,0.0000399885],"genre_scores_gemma":[0.00001459426,0.00005518547,0.1810017,0.0002650851,0.0001756427,0.0000722337,0.8182889,0.00001968512,0.000107048],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3810066,"threshold_uncertainty_score":0.9999365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.151622939362962,"score_gpt":0.2948818444379449,"score_spread":0.1432589050749829,"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."}}