{"id":"W8258861","doi":"10.7589/0090-3558-29.4.596","title":"Multi-class categorization based on cluster analysis and TFIDF","year":2008,"lang":"en","type":"article","venue":"Journal of Wildlife Diseases","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Categorization; tf–idf; Computer science; Class (philosophy); Artificial intelligence; Humanities; Information retrieval; Natural language processing; Philosophy; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009319177,0.0000973797,0.0001906768,0.0005515973,0.0001191369,0.00008687819,0.0003714999,0.00004163383,0.000009224177],"category_scores_gemma":[0.0001928882,0.00007427427,0.0001359086,0.0006817764,0.0000730036,0.0004910155,0.00004664403,0.00008395383,0.000005071911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003422143,"about_ca_system_score_gemma":0.00008737925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000300179,"about_ca_topic_score_gemma":0.00000111876,"domain_scores_codex":[0.9990698,0.00005158267,0.0002874613,0.0001554078,0.0003248067,0.0001109823],"domain_scores_gemma":[0.9990395,0.0001105022,0.0003134192,0.0002774435,0.0001463591,0.0001128011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001176577,0.001063458,0.9486263,0.00002648385,0.0003753787,0.0001059439,0.0003393163,0.01184238,0.000298319,0.002812354,0.02007776,0.01431463],"study_design_scores_gemma":[0.001069172,0.0001904135,0.7244546,0.00001662493,0.000190545,0.00001514424,0.00004723793,0.2708368,0.0003303868,0.0003287812,0.002353912,0.0001663254],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1848001,0.0002752098,0.8045701,0.009914328,0.0001708054,0.00008805321,0.000006289155,0.0001210632,0.00005399399],"genre_scores_gemma":[0.9885148,0.0001081946,0.009802012,0.001446613,0.00003840095,0.000002506271,0.000003098508,0.000004180158,0.0000801505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8037148,"threshold_uncertainty_score":0.3028817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01863920483842632,"score_gpt":0.2532088505944861,"score_spread":0.2345696457560597,"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."}}