{"id":"W3085332162","doi":"10.22148/001c.17212","title":"Can GPT-3 Pass a Writer’s Turing Test?","year":2020,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":205,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Turing test; Heuristic; Field (mathematics); Grammar; Test (biology); Artificial intelligence; Scale (ratio); Language model; Natural language processing; Natural language; Turing; Language identification; Programming language; Linguistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002836183,0.0001964754,0.0004022609,0.00007608067,0.00009416886,0.0003850571,0.001358158,0.00006208047,0.00001681297],"category_scores_gemma":[0.0004986395,0.0001328432,0.0002944052,0.0006475557,0.00005331593,0.0005963298,0.0003543173,0.0004568165,0.00001314945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001259191,"about_ca_system_score_gemma":0.0001116695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034533,"about_ca_topic_score_gemma":0.000008471317,"domain_scores_codex":[0.9981041,0.00006293324,0.0006687034,0.000245711,0.0006149987,0.0003035785],"domain_scores_gemma":[0.998153,0.0001741513,0.000439406,0.0002586436,0.0005841444,0.0003906303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002274299,0.002864481,0.09566623,0.0009391286,0.002219222,0.00859012,0.09229141,0.1251046,0.04673479,0.02430968,0.1229658,0.4780872],"study_design_scores_gemma":[0.001723491,0.001855343,0.02270716,0.0001519001,0.0001801423,0.001491966,0.001415033,0.9344832,0.003535417,0.01067262,0.02080879,0.0009749455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4494256,0.001013878,0.371239,0.17415,0.001887353,0.0003324081,0.0000171778,0.0003009899,0.001633574],"genre_scores_gemma":[0.951152,0.00003614496,0.04631538,0.001524865,0.000869702,3.979804e-7,5.968562e-7,0.000007576295,0.00009329316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8093786,"threshold_uncertainty_score":0.5417189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04380876233099833,"score_gpt":0.2608145662498129,"score_spread":0.2170058039188145,"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."}}