{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04794518,0.0003003133,0.00307067,0.00006050314,0.0001610336,0.00006029818,0.000951924,0.0007657973,0.000007433855],"category_scores_gemma":[0.09258889,0.0002022443,0.0009740933,0.0001723618,0.0003973414,0.0001880076,0.0001166548,0.002765327,0.000001262555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003687053,"about_ca_system_score_gemma":0.0003388908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001805693,"about_ca_topic_score_gemma":0.000002965892,"domain_scores_codex":[0.9801996,0.01104396,0.007246155,0.0006190173,0.000465722,0.0004254793],"domain_scores_gemma":[0.8152775,0.1708134,0.01231741,0.0006681876,0.0007630337,0.0001604412],"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":[0.0003528173,0.00007240353,0.2008512,0.0005708661,0.0007887105,0.00005513505,0.0004427294,0.0007958732,0.00009426306,0.01104091,0.7482396,0.03669551],"study_design_scores_gemma":[0.007101928,0.002132535,0.2981668,0.0009415167,0.0007156435,0.0004646307,0.0003552026,0.1279629,0.00002165997,0.1360811,0.4249737,0.001082405],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.004130734,0.0001388652,0.5407546,0.4539652,0.0006979042,0.0002521164,0.00001437401,0.00001310726,0.00003304613],"genre_scores_gemma":[0.2842861,0.0001264916,0.1565086,0.5544158,0.004539673,0.00002396247,0.00001499013,0.00003107521,0.00005330611],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.384246,"threshold_uncertainty_score":0.9995353,"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."}}