{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004680427,0.001282835,0.00273651,0.006260696,0.001796831,0.004977927,0.00318167,0.002113678,0.003873407],"category_scores_gemma":[0.01287507,0.0006909358,0.002220614,0.006034981,0.001143911,0.003821569,0.001962364,0.002338476,0.004310734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002232097,"about_ca_system_score_gemma":0.002270705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004871854,"about_ca_topic_score_gemma":0.004738296,"domain_scores_codex":[0.9931911,0.001641486,0.0005263122,0.001369658,0.002987743,0.0002837779],"domain_scores_gemma":[0.9946113,0.002018103,0.0003351234,0.00143397,0.001493816,0.0001077366],"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":[0.0001275152,0.000259846,0.002020992,0.0005035432,0.0002677781,0.0001035431,0.0004026759,0.104662,0.00502714,0.05901309,0.01979074,0.8078211],"study_design_scores_gemma":[0.0000256959,0.00007237069,0.0009725626,0.00007967422,0.00005577678,0.000314722,0.0001442897,0.8929834,0.005996895,0.06651921,0.0327519,0.00008356319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002128145,0.0004344948,0.9939262,0.0002259047,0.00008983399,0.0002336826,0.0003137919,0.001355367,0.001292565],"genre_scores_gemma":[0.03580363,0.0005568964,0.9584773,0.0001279713,0.0001463556,0.0005175219,0.001339136,0.0002296609,0.002801525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006260696,"threshold_uncertainty_score":0.02475274,"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."}}