{"id":"W2041413176","doi":"10.3115/1073445.1073470","title":"Language and task independent text categorization with simple language models","year":2003,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Categorization; Artificial intelligence; Task (project management); Language identification; Simple (philosophy); Language model; Variety (cybernetics); Independence (probability theory); Selection (genetic algorithm); Identification (biology); Feature (linguistics); Character (mathematics); Text categorization; Feature selection; Natural language; 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":[0.0002379267,0.00008534313,0.00007814626,0.00004994899,0.00008711831,0.0001071991,0.000141336,0.00004545386,0.00005039508],"category_scores_gemma":[0.00001805354,0.00006398735,0.00001164753,0.0002208868,0.00001569756,0.000388713,0.00004631644,0.00008308241,0.00001962629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001771107,"about_ca_system_score_gemma":0.00003953505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008874888,"about_ca_topic_score_gemma":0.00005149088,"domain_scores_codex":[0.9992825,0.00006397082,0.00009506159,0.0002270485,0.0001625569,0.0001688437],"domain_scores_gemma":[0.9996035,0.00002709719,0.00003623074,0.0002199286,0.00003279169,0.00008048732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004735944,0.00002881481,0.001470014,0.00001237244,0.0000111244,0.00002832031,0.0107516,0.0008562603,0.002419902,0.9759377,0.0001292703,0.00834992],"study_design_scores_gemma":[0.003604861,0.0004599752,0.003996884,0.00003995566,0.00004312044,0.0003638258,0.01516041,0.7476608,0.1628135,0.05916029,0.004911079,0.001785251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09488712,0.0001526375,0.8963147,0.0001246709,0.00003360818,0.00009696659,0.000001678957,0.0001279539,0.008260651],"genre_scores_gemma":[0.9864028,0.000004270036,0.01227799,0.0002752402,0.00001060228,0.00000503322,0.000009604252,0.000005716617,0.001008773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9167774,"threshold_uncertainty_score":0.2609329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01593452888467338,"score_gpt":0.2515908326777858,"score_spread":0.2356563037931124,"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."}}