{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003175111,0.00004710782,0.00004298691,0.00004167205,0.0001519248,0.00006306978,0.0001377647,0.00002085842,0.0000759934],"category_scores_gemma":[0.0002286041,0.00002868275,0.00001418011,0.0001198366,0.00002245264,0.0005167871,0.00008819117,0.00002696246,0.00006256654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001253738,"about_ca_system_score_gemma":0.00002362057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003133642,"about_ca_topic_score_gemma":0.000009753458,"domain_scores_codex":[0.9994872,0.0000573865,0.00009351038,0.0001492925,0.0001082345,0.0001043453],"domain_scores_gemma":[0.9995335,0.000161132,0.00002489163,0.0001755204,0.00005328725,0.00005165697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[3.384702e-7,0.000009018626,0.0006990941,0.000002539588,0.000003264069,0.000001037033,0.001212486,0.000002501529,0.004799888,0.8629068,0.000425797,0.1299372],"study_design_scores_gemma":[0.00361607,0.0004348472,0.05848316,0.0004145932,0.00008778973,0.00009292092,0.01099549,0.2487957,0.1825489,0.4597653,0.03250932,0.002255897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005238437,0.00005141726,0.9755489,0.01394276,0.00005626042,0.00006114755,0.000002078726,0.0001517237,0.004947328],"genre_scores_gemma":[0.9471333,0.000009738751,0.05127956,0.0002852516,0.0000249649,0.0000132672,0.000001361649,0.000002466761,0.001250089],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9418949,"threshold_uncertainty_score":0.1169648,"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."}}