{"id":"W2791007156","doi":"10.1111/cogs.12583","title":"A Large‐Scale Analysis of Variance in Written Language","year":2018,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Natural language processing; Semantics (computer science); Artificial intelligence; Natural language; Distributional semantics; Universal Networking Language; Language identification; Language model; Linguistics; Word (group theory); Comprehension approach; Semantic similarity; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.001036324,0.00006963942,0.0001658795,0.000576233,0.00009029296,0.00005660219,0.000947397,0.0000232849,0.00003552322],"category_scores_gemma":[0.0003043881,0.00006555366,0.00004295997,0.005463834,0.0004234247,0.0005419092,0.0003597988,0.00006928317,0.00002641973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000295028,"about_ca_system_score_gemma":0.000128855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005515297,"about_ca_topic_score_gemma":0.000247361,"domain_scores_codex":[0.9986027,0.00004101763,0.0001831614,0.0004917336,0.0003648549,0.0003164818],"domain_scores_gemma":[0.9990878,0.00008736846,0.00007417,0.0003781655,0.0003077686,0.00006478463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005159375,0.0009539681,0.2688789,0.00005136273,0.0002667573,0.0001419738,0.2862667,0.0004747164,0.1258112,0.1090961,0.00005859741,0.2079481],"study_design_scores_gemma":[0.0003403063,0.00006271751,0.2187203,0.00005512206,0.00004121103,0.000002070898,0.002046519,0.7591333,0.01833759,0.001061394,0.00002616316,0.0001732897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4753217,0.00002773513,0.52012,0.00005714627,0.00006747447,0.00004773119,0.000004696966,0.0000187987,0.004334728],"genre_scores_gemma":[0.9837423,0.000001560599,0.01588113,0.0002586539,0.00002562723,0.000004768834,6.095192e-7,0.000001876135,0.00008345347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7586586,"threshold_uncertainty_score":0.2673201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01775587779283431,"score_gpt":0.3001291638628089,"score_spread":0.2823732860699746,"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."}}