{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09318127,0.001548775,0.001729398,0.001740954,0.004517208,0.003124069,0.002968075,0.003210018,0.02164105],"category_scores_gemma":[0.2287324,0.001652051,0.001118258,0.001570784,0.004207343,0.003804295,0.004586227,0.002077196,0.01029814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007282454,"about_ca_system_score_gemma":0.002455533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001547742,"about_ca_topic_score_gemma":0.005889078,"domain_scores_codex":[0.9133309,0.05957136,0.00766905,0.006028268,0.01084868,0.002551867],"domain_scores_gemma":[0.8220478,0.1033283,0.01063095,0.03945228,0.02144393,0.003096654],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.02055983,0.01243049,0.1679749,0.009989399,0.001244442,0.003028166,0.07567944,0.002669072,0.1019154,0.03621518,0.1171823,0.4511114],"study_design_scores_gemma":[0.00825065,0.01698867,0.3695358,0.003613965,0.001333594,0.003124264,0.01581505,0.02091968,0.07757652,0.08778652,0.3942222,0.0008329982],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4419166,0.002488095,0.3625718,0.008088436,0.003481058,0.1272035,0.00450668,0.003727734,0.04601609],"genre_scores_gemma":[0.5567074,0.000575347,0.1979051,0.00949976,0.0009017205,0.221252,0.00217736,0.0006566586,0.01032465],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9068187,"threshold_uncertainty_score":0.4927955,"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."}}