{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1027529,0.0006506172,0.0006200272,0.001457094,0.003461851,0.003837367,0.002108326,0.002012962,0.004008075],"category_scores_gemma":[0.3696686,0.000532731,0.0007921914,0.001431823,0.00480962,0.004332073,0.004127893,0.001669818,0.001633172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003637357,"about_ca_system_score_gemma":0.007192378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006617405,"about_ca_topic_score_gemma":0.007571625,"domain_scores_codex":[0.911775,0.06125987,0.004513669,0.006010805,0.01402748,0.002413225],"domain_scores_gemma":[0.5380709,0.2631588,0.06621211,0.06435283,0.05775492,0.0104505],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01073581,0.004766226,0.6773686,0.0009585178,0.0003436371,0.0004171143,0.03926376,0.003100681,0.009635587,0.01254944,0.02084264,0.2200179],"study_design_scores_gemma":[0.003563343,0.01670644,0.7735194,0.0007925272,0.0006084148,0.0005244828,0.03533232,0.04698468,0.02433159,0.01703208,0.08013196,0.0004729026],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.969835,0.0001105775,0.01484604,0.002349334,0.0002033665,0.002842549,0.0003973521,0.00056273,0.008853104],"genre_scores_gemma":[0.9705383,0.00004333806,0.02292212,0.0007671397,0.00008487689,0.003310305,0.0003765536,0.0001602369,0.001797103],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8972471,"threshold_uncertainty_score":0.5434158,"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."}}