{"id":"W3010283858","doi":"10.1016/j.jclinepi.2020.02.009","title":"Quality control for crowdsourcing citation screening: the importance of assessment number and qualification set size","year":2020,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Agricultural Research Institute of Ontario; Children's Hospital of Eastern Ontario; University of British Columbia; BC Children's Hospital","funders":"CHEO Research Institute","keywords":"Crowdsourcing; Citation; Computer science; Redundancy (engineering); Quality (philosophy); Set (abstract data type); Data science; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","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":["metaresearch"],"category_scores_codex":[0.2576164,0.0006606637,0.003255617,0.003535693,0.003961674,0.007669971,0.00645936,0.02711598,0.005043806],"category_scores_gemma":[0.7273055,0.001107629,0.003231249,0.003511008,0.008895122,0.006343049,0.003115242,0.02676823,0.001963971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00815346,"about_ca_system_score_gemma":0.01467715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02177478,"about_ca_topic_score_gemma":0.02596999,"domain_scores_codex":[0.7059871,0.1992484,0.02549467,0.01337871,0.0525864,0.003304711],"domain_scores_gemma":[0.1091238,0.8221013,0.01472305,0.01403364,0.03614629,0.003871978],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.002293103,0.000323048,0.04083046,0.001909012,0.0007680905,0.001277741,0.003654968,0.001537266,0.0009348494,0.05108152,0.5054771,0.3899128],"study_design_scores_gemma":[0.003062152,0.001802235,0.09544592,0.01115148,0.00178515,0.00504915,0.002926148,0.07097718,0.004634204,0.3421862,0.4599843,0.0009958798],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.006084798,0.004552508,0.02111423,0.9484307,0.01144945,0.0003430259,0.0004344916,0.0002170834,0.007373657],"genre_scores_gemma":[0.2324224,0.00330051,0.05519373,0.6501433,0.05137278,0.001985851,0.000286443,0.0003648171,0.004930217],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7423836,"threshold_uncertainty_score":0.9154912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3021707952112088,"score_gpt":0.5062694162139675,"score_spread":0.2040986210027587,"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."}}