{"id":"W2527936838","doi":"10.63317/4e2puhxuby8y","title":"Discriminating Similar Languages: Evaluations and Explorations","year":2016,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Oracle; Digital subscriber line; Annotation; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02576143,0.004389539,0.003231489,0.006945222,0.001886513,0.004616154,0.002964584,0.003693311,0.002191132],"category_scores_gemma":[0.08654507,0.0007557407,0.001788765,0.005445751,0.001937109,0.006718908,0.004313369,0.002526149,0.002034829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001870571,"about_ca_system_score_gemma":0.001330283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006661866,"about_ca_topic_score_gemma":0.006729185,"domain_scores_codex":[0.9582401,0.02457889,0.003253248,0.004968994,0.006813744,0.002144941],"domain_scores_gemma":[0.900428,0.07429386,0.002353644,0.01172543,0.009033212,0.002165768],"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":[0.007581749,0.003888005,0.0602864,0.003227945,0.002147167,0.001466282,0.003687308,0.1359321,0.02103069,0.003962701,0.04290391,0.7138858],"study_design_scores_gemma":[0.0006966834,0.003284429,0.03617486,0.0006697603,0.00102927,0.002607484,0.005197299,0.8647785,0.0443079,0.02266376,0.01812195,0.0004680755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8927265,0.01749084,0.06058958,0.001680552,0.0004931168,0.0005379546,0.003722861,0.008498242,0.01426031],"genre_scores_gemma":[0.9315621,0.001480379,0.05352144,0.0004541501,0.0001907402,0.0002256325,0.008559514,0.001360175,0.002645771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02576143,"threshold_uncertainty_score":0.1362411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05894784463913573,"score_gpt":0.3522310635662659,"score_spread":0.2932832189271302,"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."}}