{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002337298,0.001509378,0.001167884,0.002045991,0.0008253244,0.001713808,0.002123871,0.001941533,0.004718918],"category_scores_gemma":[0.007915046,0.0005162295,0.001770063,0.001522449,0.0008695837,0.004034683,0.002580086,0.001773308,0.005482635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004869291,"about_ca_system_score_gemma":0.001305411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001182922,"about_ca_topic_score_gemma":0.002875791,"domain_scores_codex":[0.9976329,0.0007488006,0.0001570341,0.0005941322,0.0006986551,0.0001685146],"domain_scores_gemma":[0.9966821,0.001340087,0.0002556035,0.0009581537,0.0005762494,0.0001878363],"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":[0.0004319178,0.0006311986,0.002153967,0.0004250611,0.0003145985,0.0002250059,0.0003941887,0.02889732,0.07072942,0.009486802,0.01196257,0.874348],"study_design_scores_gemma":[0.00009453876,0.0003941922,0.002208825,0.00004735649,0.0001077648,0.0004538406,0.0001713372,0.9080892,0.04037616,0.03721933,0.01070181,0.0001356991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01173601,0.0001923304,0.9823314,0.0001633732,0.0001183709,0.0001893619,0.0002968798,0.003727485,0.001244913],"genre_scores_gemma":[0.1596035,0.0001849785,0.830322,0.0003318561,0.0002609791,0.000650864,0.001963203,0.0003170249,0.00636557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004718918,"threshold_uncertainty_score":0.01578641,"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."}}