{"id":"W1845278523","doi":"10.1007/3-540-70659-3_58","title":"Document Classification Using Phrases","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Grammar; Classifier (UML); Naive Bayes classifier; Bayes classifier; Pattern recognition (psychology); Linguistics; Support vector machine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004736306,0.0004791869,0.0004054573,0.001116065,0.00029866,0.0008326078,0.003598462,0.0003568641,0.00008039853],"category_scores_gemma":[0.00008430146,0.000443213,0.000118358,0.0007463154,0.0007339805,0.001050685,0.001088776,0.0005828285,0.0001298837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006046181,"about_ca_system_score_gemma":0.000254354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001110909,"about_ca_topic_score_gemma":0.000007180289,"domain_scores_codex":[0.9963338,0.00002495903,0.0005786484,0.00150885,0.0009856835,0.0005680876],"domain_scores_gemma":[0.9971371,0.0002368515,0.0004358613,0.001903056,0.0001724835,0.0001146347],"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":[0.000001534555,0.00002966814,0.00005445954,0.00001896974,0.000008185415,0.0000216188,0.0002444897,0.003035423,0.0005633286,0.185598,0.0000549757,0.8103693],"study_design_scores_gemma":[0.0002442487,0.000110481,0.0001535877,0.0002500393,0.00001122932,0.00004869391,5.682325e-7,0.623833,0.004045157,0.364692,0.005768163,0.0008428037],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001081614,0.0005052806,0.9913718,0.001633555,0.00106744,0.0003618735,0.00000220771,0.0005553152,0.004394335],"genre_scores_gemma":[0.3718683,0.0002683616,0.6251376,0.0008307314,0.0003212054,0.00002149905,0.000006370861,0.00004379329,0.001502179],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8095265,"threshold_uncertainty_score":0.999802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04930136608321829,"score_gpt":0.2785514953889736,"score_spread":0.2292501293057553,"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."}}