{"id":"W2250996967","doi":"","title":"Cognate and Misspelling Features for Natural Language Identification","year":2013,"lang":"en","type":"article","venue":"Workshop on Innovative Use of NLP for Building Educational Applications","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Bigram; Computer science; Cognate; Natural language processing; Artificial intelligence; Classifier (UML); Natural language; Word (group theory); Identification (biology); Spelling; Syntax; Language identification; Linguistics","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":[0.0002985854,0.0001341796,0.0001367861,0.0002374369,0.0002917865,0.0001976263,0.000322163,0.00006890909,0.000008616888],"category_scores_gemma":[0.0004480996,0.0001314282,0.00004862241,0.000890872,0.00007392446,0.0004511646,0.00004568437,0.0001358297,0.000007760941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005168972,"about_ca_system_score_gemma":0.00008788993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009297542,"about_ca_topic_score_gemma":0.000001177307,"domain_scores_codex":[0.9989144,0.00002306261,0.000349987,0.0003835883,0.0001443136,0.00018463],"domain_scores_gemma":[0.9967404,0.001542678,0.000300702,0.0002941905,0.001070455,0.00005159171],"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":[0.000009355132,0.00007984566,0.000113372,0.00004204475,0.00002600465,7.732403e-9,0.0004405445,0.00009198696,0.01995312,0.9281286,0.004231504,0.04688362],"study_design_scores_gemma":[0.002106603,0.000194079,0.1308183,0.000627221,0.00008739412,0.00002025552,0.001771845,0.08365323,0.2036726,0.486727,0.08844929,0.001872165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0442637,0.0002813015,0.9408898,0.01235607,0.0002405623,0.001786059,0.00007078966,0.00006184285,0.00004990186],"genre_scores_gemma":[0.7602218,0.000008716002,0.2361488,0.0003857027,0.0001292208,0.00167934,0.0002178627,0.00001280803,0.00119575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7159581,"threshold_uncertainty_score":0.5359487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04016925118674335,"score_gpt":0.347697391551569,"score_spread":0.3075281403648256,"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."}}