{"id":"W3016943666","doi":"10.1109/infoteh48170.2020.9066277","title":"Language Distance using Common N-Grams Approach","year":2020,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Authorship attribution; Similarity (geometry); Natural language processing; Measure (data warehouse); Phenomenon; Artificial intelligence; Stability (learning theory); Data mining; Machine learning","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":[0.001111926,0.0009479225,0.00101444,0.01058944,0.001625755,0.002194935,0.001350334,0.001398862,0.004312257],"category_scores_gemma":[0.008567459,0.0002866805,0.0008856753,0.00702726,0.000677119,0.003852058,0.002484967,0.001339929,0.002924245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009974759,"about_ca_system_score_gemma":0.001108524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005612133,"about_ca_topic_score_gemma":0.007656438,"domain_scores_codex":[0.9968228,0.000651822,0.0003084541,0.0009542504,0.00100633,0.0002562007],"domain_scores_gemma":[0.9965457,0.001196676,0.0004103416,0.0007174711,0.0009549832,0.0001748478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006373965,0.0004725023,0.03076203,0.0006051142,0.0005090332,0.0008162512,0.002113872,0.03377767,0.01778127,0.06641632,0.01537994,0.8307287],"study_design_scores_gemma":[0.00005531702,0.0002714056,0.02293553,0.0001793444,0.0002137096,0.001493018,0.001838813,0.7291842,0.01906468,0.1793744,0.04519818,0.0001915005],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1895954,0.00236234,0.7838391,0.0004644445,0.0004013012,0.0003724702,0.00387004,0.00410187,0.01499301],"genre_scores_gemma":[0.7262477,0.0006210594,0.2595993,0.0001047388,0.0001620467,0.0002841994,0.004662524,0.000447725,0.007870734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01058944,"threshold_uncertainty_score":0.01442587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07502179611688059,"score_gpt":0.3015637118232853,"score_spread":0.2265419157064047,"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."}}