{"id":"W4398686134","doi":"10.7910/dvn/k0oyqf/riy9zp","title":"questions-words.txt","year":2019,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Word (group theory); Ideology; Linguistics; Computer science; Natural language processing; Word length; Artificial intelligence; Philosophy; Political science; Politics; Law","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002238762,0.0004220071,0.0005796459,0.0002896922,0.0003348773,0.0004437885,0.0008260591,0.0001314199,0.4625328],"category_scores_gemma":[0.0001805174,0.0003629344,0.0002529932,0.000051878,0.0004478075,0.0004148325,0.000526685,0.000427347,0.6226526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006646661,"about_ca_system_score_gemma":0.00008818239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001856765,"about_ca_topic_score_gemma":0.00669502,"domain_scores_codex":[0.9981664,0.00008798091,0.0003813393,0.0005356426,0.0004541211,0.0003745266],"domain_scores_gemma":[0.9976349,0.00009293,0.0002613814,0.001800147,0.0001342515,0.00007635629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009366362,0.00008871129,9.505417e-7,0.0001138436,0.0004812392,0.00006818101,0.0008668534,0.000003925449,1.763243e-7,0.005085314,0.993116,0.0001654942],"study_design_scores_gemma":[0.0001758719,0.00003241452,0.000001301102,0.0001422626,0.0007956917,0.000002865089,0.003172826,0.000004242743,4.133625e-7,0.00007027944,0.9951509,0.0004509862],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000002577452,0.00001355392,0.000003371814,0.0000118954,0.002421727,0.0002117674,0.9630765,0.00006633494,0.03419232],"genre_scores_gemma":[0.00002062038,0.0005712189,0.00003038448,0.0005908327,0.002131148,0.00003537908,0.9662304,0.00003178266,0.03035824],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1601199,"threshold_uncertainty_score":0.9998823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02796877507691603,"score_gpt":0.2720210053034471,"score_spread":0.2440522302265311,"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."}}