{"id":"W4214833826","doi":"10.31234/osf.io/48yxj","title":"Evaluating CloudResearch’s Approved Group as a Solution for Problematic Data Quality on MTurk","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Vetting; Honesty; Data quality; Reliability (semiconductor); Sample (material); Quality (philosophy); Psychology; Medicine; Applied psychology; Computer science; Social psychology; Engineering; Computer security; Operations management","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009522653,0.0004080985,0.0006321814,0.0001468142,0.0004278981,0.001699101,0.003169557,0.0003252552,0.0000210555],"category_scores_gemma":[0.003139853,0.0003733286,0.0002176396,0.0002734034,0.00006854043,0.0003502724,0.007546062,0.0008916239,0.00002959693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002106841,"about_ca_system_score_gemma":0.0007650162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008961864,"about_ca_topic_score_gemma":0.0001603831,"domain_scores_codex":[0.9940313,0.0009695936,0.0008633143,0.002230476,0.001203718,0.0007016034],"domain_scores_gemma":[0.9920996,0.001181582,0.0004732583,0.005609599,0.0004549093,0.0001810292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002471553,0.001801221,0.00005167876,0.01397791,0.0007296921,0.00004314919,0.008845078,0.03174279,0.04920354,0.1357815,0.01091525,0.746661],"study_design_scores_gemma":[0.000510196,0.0001942976,0.00008363385,0.0009633667,0.00003098861,0.00001014072,0.0001681137,0.9795718,0.001003918,0.01677547,0.0002220421,0.0004660132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02879047,0.0001358194,0.963201,0.002492786,0.0008423956,0.002204737,0.00002305989,0.0004292443,0.001880463],"genre_scores_gemma":[0.4244383,0.000009215929,0.572888,0.0004565025,0.0003039961,0.0003837162,0.0006005891,0.00004355457,0.0008761138],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.947829,"threshold_uncertainty_score":0.9998719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3965886447347578,"score_gpt":0.4798312497970436,"score_spread":0.08324260506228576,"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."}}