{"id":"W2041812559","doi":"10.2298/psi1004441s","title":"Using Amazon Mechanical Turk for linguistic research","year":2010,"lang":"en","type":"article","venue":"Psihologija","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":110,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Predictability; Sentence; Computer science; Natural language processing; Artificial intelligence; Set (abstract data type); Consistency (knowledge bases); Lift (data mining); Task (project management); Context (archaeology); Linguistics; Mathematics; Statistics; Data mining; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008004748,0.0001204769,0.0001630321,0.000116313,0.0003372409,0.0000449422,0.0004782359,0.0002068486,0.00009690379],"category_scores_gemma":[0.014705,0.00009604271,0.00007883098,0.0001956295,0.0003544088,0.00003684708,0.0001632617,0.0007564622,0.00008453354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001287159,"about_ca_system_score_gemma":0.00005461441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000238791,"about_ca_topic_score_gemma":0.00001887592,"domain_scores_codex":[0.9982852,0.0002053067,0.0001943334,0.0005767322,0.000183773,0.0005546487],"domain_scores_gemma":[0.9977258,0.001615441,0.00005225263,0.0004022355,0.0001130853,0.00009120527],"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":[0.00003631753,0.00005656619,0.00005121156,0.000007617927,0.000001083726,0.0002863664,0.0001233678,0.000001056915,0.9932131,0.005174287,0.0001924225,0.0008565672],"study_design_scores_gemma":[0.0003617926,0.0002559383,0.00003789185,0.000006944829,0.000009011093,0.0005252331,0.00003981304,0.0006483071,0.9617026,0.02363461,0.0126059,0.0001719495],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951254,0.00001694132,0.0003288856,0.0004150522,0.001762166,0.0003600049,0.0000172619,0.0001283355,0.001846003],"genre_scores_gemma":[0.9929186,0.000005370233,0.004888883,0.001033147,0.0007920452,0.00002133015,0.000002498409,0.0000212776,0.0003168892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03151053,"threshold_uncertainty_score":0.9935946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.378289803714537,"score_gpt":0.4979801031158871,"score_spread":0.1196902994013501,"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."}}