{"id":"W2106568252","doi":"10.1017/s1930297500002205","title":"Running experiments on Amazon Mechanical Turk","year":2010,"lang":"en","type":"article","venue":"Judgment and Decision Making","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":3803,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Amazon rainforest; Subject (documents); Data science; Quality (philosophy); Social media; Population; Computer science; Data quality; Internet privacy; World Wide Web; Engineering; Sociology; Operations management; Physics; Demography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0106002,0.001559696,0.001898138,0.0007777961,0.001784908,0.002230315,0.002565708,0.001372955,0.02014782],"category_scores_gemma":[0.04026874,0.0009738531,0.001243727,0.00119031,0.001015439,0.00256223,0.001532059,0.001801443,0.008907505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009584744,"about_ca_system_score_gemma":0.002218887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004810431,"about_ca_topic_score_gemma":0.005902929,"domain_scores_codex":[0.9896137,0.004968881,0.0009775196,0.002216916,0.001455113,0.0007679908],"domain_scores_gemma":[0.9476895,0.03220091,0.001809316,0.01164565,0.004485559,0.00216905],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.02518583,0.03481211,0.04343781,0.00491023,0.002266456,0.001598976,0.006690448,0.1505556,0.07589578,0.01523245,0.164472,0.4749424],"study_design_scores_gemma":[0.01133728,0.01736218,0.1137468,0.0005658848,0.001148469,0.0004123056,0.003766337,0.5784165,0.03766168,0.07417274,0.1603394,0.001070406],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.803151,0.0008217875,0.1037292,0.001758356,0.001412066,0.01406483,0.01034818,0.0115714,0.05314323],"genre_scores_gemma":[0.8539557,0.0002688378,0.1083155,0.0009277457,0.0002579814,0.01539392,0.008905047,0.0009156841,0.0110597],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9893998,"threshold_uncertainty_score":0.06740123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0201525776565425,"score_gpt":0.293849149241808,"score_spread":0.2736965715852655,"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."}}