{"id":"W2099126842","doi":"10.1109/icdm.2001.989592","title":"A simple KNN algorithm for text categorization","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":225,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Interpretability; Artificial intelligence; Text categorization; Feature (linguistics); Context (archaeology); Vocabulary; Feature selection; Word (group theory); Categorization; Simple (philosophy); Class (philosophy); k-nearest neighbors algorithm; Process (computing); Machine learning; Natural language processing; Pattern recognition (psychology); Mathematics","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":[0.00005089884,0.00006147106,0.00005853032,0.00007360875,0.00009079086,0.0001246442,0.000437138,0.00004453016,0.0001445838],"category_scores_gemma":[0.00002573412,0.00005180555,0.00002965318,0.0002641226,0.00001873607,0.0003942382,0.00006833048,0.00002767173,0.0001760096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001887051,"about_ca_system_score_gemma":0.000005316641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005505789,"about_ca_topic_score_gemma":0.000001469667,"domain_scores_codex":[0.9994497,0.000005638633,0.0001127411,0.0002000874,0.00008970848,0.0001421273],"domain_scores_gemma":[0.9995209,0.00004045247,0.00004043352,0.0003235185,0.00005028878,0.00002441642],"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":[7.980512e-8,0.00002095014,0.00002854779,0.000001155663,0.000001979119,1.347503e-7,0.00004584582,0.000001362672,0.0001356888,0.3066415,0.01653753,0.6765852],"study_design_scores_gemma":[0.0002315967,0.0000584793,0.0001912395,7.566895e-7,0.000001771454,0.000001494343,0.00004645347,0.8083091,0.00974343,0.04754684,0.1337463,0.0001225462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00007800005,0.00003147982,0.9915096,0.002448056,0.00009333993,0.00016533,0.000001304503,0.0008307786,0.004842147],"genre_scores_gemma":[0.6075973,0.00003884285,0.3773731,0.0004594227,0.00005140491,0.0001427332,0.00001033092,0.000008625558,0.01431825],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8083078,"threshold_uncertainty_score":0.2262306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03016497877693925,"score_gpt":0.2537802900861292,"score_spread":0.22361531130919,"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."}}