{"id":"W6958680415","doi":"10.6084/m9.figshare.c.3968838.v1","title":"Effectiveness of en masse versus two-step retraction: a systematic review and meta-analysis","year":2018,"lang":"en","type":"other","venue":"Figshare","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Randomized controlled trial; Significant difference; Quality assessment; Mean difference; Closure (psychology); Prospective cohort study; Incisor; Qualitative analysis","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch","research_integrity"],"domain":"evaluation","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch","research_integrity"],"domain":"evaluation","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009070621,0.000575004,0.005391288,0.0005989726,0.00003002032,0.00004217463,0.0004176672,0.0004078132,0.6952773],"category_scores_gemma":[0.003746478,0.0004347519,0.001566167,0.001296291,0.00001798146,0.00008690377,0.0001471643,0.0002364095,0.035522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001380084,"about_ca_system_score_gemma":0.00005508469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005865356,"about_ca_topic_score_gemma":0.0001434784,"domain_scores_codex":[0.9957118,0.002157897,0.0006009837,0.0006703612,0.0006311134,0.0002278143],"domain_scores_gemma":[0.9954594,0.0009267943,0.001742653,0.001442684,0.00031973,0.0001087427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.00001238041,0.00001299756,1.242503e-7,0.474294,0.139192,0.000006769356,0.000002699558,2.347372e-7,0.000001144527,0.000001515283,0.386476,1.613661e-7],"study_design_scores_gemma":[0.0003514274,0.00005452863,0.000008889131,0.1619004,0.8000273,0.000009395656,0.00000411271,0.000008465506,0.00001773505,7.187357e-7,0.03722853,0.0003885153],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[7.248185e-8,0.2713556,0.000001270877,0.000005114303,0.00004554755,0.004120166,0.603923,0.0002105606,0.1203386],"genre_scores_gemma":[0.0006099975,0.0004520011,0.0003373242,0.00006135124,0.0003268372,0.009212582,0.3486876,0.003164229,0.637148],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.6608353,"threshold_uncertainty_score":0.9998104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.095379647178518,"score_gpt":0.3603963959242353,"score_spread":0.2650167487457173,"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."}}