{"id":"W3080121639","doi":"10.1016/j.metip.2020.100032","title":"Reducing the number of non-naïve participants in Mechanical Turk samples","year":2020,"lang":"en","type":"article","venue":"Methods in Psychology","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.002185184,0.00009326164,0.0002760076,0.00004857783,0.00001878035,0.00001181422,0.0009450446,0.0001008419,0.00003857794],"category_scores_gemma":[0.0006617932,0.00007198819,0.00004426274,0.0005121279,0.00005281577,0.00007108768,0.0002630664,0.0003251864,0.00001201016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001330536,"about_ca_system_score_gemma":0.00002719542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001056683,"about_ca_topic_score_gemma":0.00001421082,"domain_scores_codex":[0.9976571,0.0009852095,0.0004697331,0.0004574461,0.0001056768,0.0003248627],"domain_scores_gemma":[0.9986104,0.0006286136,0.00009131303,0.0005952961,0.00001830673,0.00005606421],"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":[0.00005528655,0.0001669425,0.01790876,0.00003401011,0.00002518667,0.00004424037,0.0154631,0.001767081,0.046019,0.04722617,0.0003080164,0.8709822],"study_design_scores_gemma":[0.001492788,0.0001240625,0.04688448,0.00007646908,0.00001090677,0.00003756987,0.0002935662,0.7593675,0.01847591,0.1712815,0.001605688,0.000349555],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.108061,0.00004818166,0.884582,0.005702943,0.0004777164,0.0001037358,3.72032e-7,0.00001983735,0.001004122],"genre_scores_gemma":[0.4105769,0.000008198866,0.587961,0.001395677,0.00003766768,0.00001329663,8.44178e-8,0.000004230865,0.000002925924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8706326,"threshold_uncertainty_score":0.2935593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2570277674644276,"score_gpt":0.5170510327490248,"score_spread":0.2600232652845971,"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."}}