{"id":"W2571802872","doi":"","title":"Running experiments on Amazon Mechanical Turk","year":2010,"lang":"en","type":"article","venue":"RePub (Erasmus University, Rotterdam)","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Subject (documents); Amazon rainforest; Data science; Quality (philosophy); Computer science; Data quality; Population; Social media; Internet privacy; World Wide Web; Engineering; Sociology; Operations management; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003055762,0.0002550184,0.0002412407,0.0002638497,0.0005091064,0.0002543927,0.001110275,0.0001827027,0.00008302642],"category_scores_gemma":[0.00003187727,0.0002743326,0.0001487365,0.0004218642,0.0000678686,0.0004260312,0.0006445131,0.0006053871,0.0001539987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109896,"about_ca_system_score_gemma":0.0000690684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007655962,"about_ca_topic_score_gemma":0.00001521327,"domain_scores_codex":[0.9980445,0.00008146912,0.0001858807,0.0007465031,0.0004359698,0.0005057084],"domain_scores_gemma":[0.9983271,0.00008754592,0.000119234,0.001116753,0.00008679282,0.0002625365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002086333,0.0009664085,0.002836027,0.00005257705,0.0001947061,0.002401262,0.005651666,0.000507214,0.6729788,0.2399404,0.02237349,0.05188877],"study_design_scores_gemma":[0.009369542,0.001531848,0.009911434,0.00054086,0.0001191095,0.0007970153,0.002212401,0.0687412,0.6439788,0.003331926,0.255424,0.004041924],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9522228,0.00001112339,0.02791133,0.0009973544,0.001965233,0.0002100589,0.000001526822,0.000561103,0.01611943],"genre_scores_gemma":[0.9907699,0.000003762679,0.006215853,0.0005306752,0.000194302,0.000001040233,0.000002942858,0.00001975277,0.002261827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2366085,"threshold_uncertainty_score":0.9999709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009527346176419857,"score_gpt":0.21279727165627,"score_spread":0.2032699254798501,"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."}}