{"id":"W1826301668","doi":"10.1109/ijcnn.2003.1223678","title":"A comparison of SOM based document categorization systems","year":2004,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Artificial intelligence; Self-organizing map; Architecture; Feature (linguistics); Feature vector; Space (punctuation); Unsupervised learning; Text categorization; Machine learning; Data mining; Pattern recognition (psychology); Cluster analysis","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":[0.00008988882,0.00006453174,0.0001181423,0.0001088869,0.00004067412,0.00008795803,0.0004673543,0.00004400665,0.000009299244],"category_scores_gemma":[0.0000152281,0.00005274698,0.00002522991,0.0003138357,0.00003010192,0.0002798077,0.00005915899,0.00003721156,0.00003256743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005735784,"about_ca_system_score_gemma":0.00006090372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008561263,"about_ca_topic_score_gemma":0.000003891031,"domain_scores_codex":[0.9992734,0.00001339093,0.0002463638,0.0001627457,0.0002025587,0.0001015169],"domain_scores_gemma":[0.9993683,0.00002112849,0.000128813,0.0003958304,0.0000629248,0.00002301211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[9.240194e-7,0.00007232205,0.001614875,0.00001338808,0.000003409717,2.112823e-7,0.0001144075,0.006494985,0.002193197,0.9861835,0.0002308067,0.003077962],"study_design_scores_gemma":[0.00197732,0.0004653873,0.005525938,0.00006741304,0.00001356049,0.00000224083,0.001107636,0.1997215,0.7160572,0.06589726,0.008684771,0.0004797735],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006979523,0.0000853411,0.9888121,0.001652857,0.0001762305,0.0001462335,2.766986e-7,0.0004501107,0.001697339],"genre_scores_gemma":[0.972618,0.000002421736,0.02717023,0.00002973167,0.000005593873,0.00001918978,0.000002923281,0.00000238677,0.0001494885],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9656385,"threshold_uncertainty_score":0.2150959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03131328734871104,"score_gpt":0.3084639845942755,"score_spread":0.2771506972455645,"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."}}