{"id":"W1537473998","doi":"10.1007/11510888_57","title":"Text Classification Using Small Number of Features","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Information retrieval","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":[0.0004752474,0.00040443,0.0004410162,0.0007372057,0.0001614495,0.0003145414,0.00346643,0.0004362631,0.00003838231],"category_scores_gemma":[0.00008793695,0.000368271,0.0001271134,0.00070431,0.0008519858,0.0005637482,0.0009306958,0.0006023985,0.00004441568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003005693,"about_ca_system_score_gemma":0.0004059716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001874712,"about_ca_topic_score_gemma":0.00003236939,"domain_scores_codex":[0.9970998,0.00002312846,0.0005828622,0.001148651,0.0007090988,0.0004365246],"domain_scores_gemma":[0.9971917,0.0002440697,0.0005687069,0.001639815,0.0002754907,0.00008022079],"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":[0.000002834721,0.00002900938,0.0001879043,0.00002381911,0.000007710465,0.000004828353,0.0002262119,0.002166117,0.001333179,0.1902351,0.00002594916,0.8057573],"study_design_scores_gemma":[0.00053699,0.0001346945,0.003133937,0.0006565565,0.00002815349,0.0001777282,0.000001838638,0.513264,0.0244604,0.4490279,0.007032197,0.001545624],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004240463,0.0003378017,0.9901348,0.00113127,0.0006466002,0.0002738206,0.000003328635,0.0002772913,0.006771073],"genre_scores_gemma":[0.3047043,0.00007889208,0.6937578,0.0003329066,0.0002129532,0.000006418573,0.000004077131,0.00002565378,0.0008770115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8042117,"threshold_uncertainty_score":0.9998769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04001810016554461,"score_gpt":0.2860904354397913,"score_spread":0.2460723352742467,"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."}}