{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01595167,0.001433678,0.002502463,0.00355971,0.003468981,0.004077507,0.00286981,0.00131172,0.4508859],"category_scores_gemma":[0.04857332,0.0008561609,0.001077128,0.00455449,0.001541274,0.004827495,0.00480343,0.001869786,0.2880619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217109,"about_ca_system_score_gemma":0.005948339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005246653,"about_ca_topic_score_gemma":0.009871537,"domain_scores_codex":[0.98777,0.00492792,0.001447674,0.001658677,0.003455495,0.0007402408],"domain_scores_gemma":[0.9437843,0.01404815,0.001992483,0.02046689,0.01715929,0.002548916],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005501852,0.0003767606,0.001636854,0.000984448,0.00008735566,0.0004416598,0.001505475,0.0002605987,0.003065174,0.007681395,0.8355163,0.1478939],"study_design_scores_gemma":[0.0004829757,0.0002381043,0.01344607,0.0003208609,0.00003993355,0.0002710291,0.00115388,0.001835435,0.001070592,0.01251086,0.9684815,0.0001487779],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.02536065,0.001427941,0.08014756,0.01014524,0.003966533,0.04822488,0.2546014,0.02634281,0.5497829],"genre_scores_gemma":[0.1297159,0.001714731,0.1794872,0.007902543,0.002354081,0.1832736,0.1668353,0.01070073,0.3180159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9840483,"threshold_uncertainty_score":0.7832446,"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."}}