{"id":"W68431266","doi":"","title":"Model Based Document Classification and Clustering","year":2008,"lang":"en","type":"article","venue":"International journal of tomography and simulation","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Cluster analysis; Computer science; Weighting; Pattern recognition (psychology); Dimensionality reduction; Artificial intelligence; Naive Bayes classifier; Classifier (UML); Data mining; Document clustering; Document classification; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001697319,0.0000696985,0.00008258277,0.0004073996,0.00007915193,0.0001044041,0.0002836573,0.00004407039,0.000002542057],"category_scores_gemma":[0.0000373225,0.00006130176,0.00004942043,0.0001211479,0.00006160076,0.0008451464,0.00005582867,0.00007886389,4.317641e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002199079,"about_ca_system_score_gemma":0.00002630571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001475994,"about_ca_topic_score_gemma":7.023175e-7,"domain_scores_codex":[0.9992086,0.00001948631,0.0002810781,0.0001190388,0.0003071944,0.00006465235],"domain_scores_gemma":[0.9992702,0.00007974685,0.0002559999,0.0001013304,0.0002515472,0.00004115555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001961271,0.000215851,0.08342212,0.000022166,0.000180699,0.00004061152,0.001723661,0.5028161,0.005522724,0.08025261,0.0002759426,0.3253314],"study_design_scores_gemma":[0.0004456209,0.00004753661,0.04710213,0.00001657904,0.000004369567,0.00003109562,0.00002322114,0.9430942,0.0002931644,0.008505279,0.0003710696,0.00006573898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2212326,0.0001497893,0.7764999,0.001782134,0.0001480946,0.00004052457,7.226107e-7,0.00003669592,0.0001095732],"genre_scores_gemma":[0.9619962,0.0001522565,0.03767585,0.0001228008,0.00003096687,0.000001746692,0.000001241383,0.000002642405,0.00001630944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7407636,"threshold_uncertainty_score":0.2499813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03912766990925967,"score_gpt":0.292956668367835,"score_spread":0.2538289984585753,"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."}}