{"id":"W142552274","doi":"10.1007/978-3-642-41062-8_19","title":"Text Categorization via Similarity Search","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Similarity (geometry); Cluster analysis; Categorization; Centroid; Outlier; Preprocessor; Metric (unit); Similarity measure; Point (geometry); Text categorization; Class (philosophy); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005826781,0.0004302993,0.0003739538,0.000964564,0.0002974456,0.000905687,0.004214925,0.0004525345,0.0001164656],"category_scores_gemma":[0.00007499578,0.0003853583,0.00008996726,0.0008464433,0.0007790233,0.001136198,0.001661406,0.0008505741,0.0004343912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003364312,"about_ca_system_score_gemma":0.0003861587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004474799,"about_ca_topic_score_gemma":0.00002325588,"domain_scores_codex":[0.9964583,0.00002922412,0.0004617668,0.001423082,0.001020785,0.0006068524],"domain_scores_gemma":[0.997292,0.0002476168,0.0002203174,0.001762409,0.0003477767,0.0001298724],"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":[9.734097e-7,0.00002037691,0.00005445812,0.00001788531,0.000004758585,0.000009738154,0.0002257936,0.002677479,0.0003307878,0.1292464,0.00009233466,0.867319],"study_design_scores_gemma":[0.0001598488,0.00011101,0.0003536148,0.0000717494,0.00000388468,0.00002078606,2.448802e-7,0.5153852,0.006576908,0.4734844,0.003219196,0.0006131771],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00004253896,0.000198643,0.9891723,0.003035065,0.0009487636,0.0004531645,0.000001808013,0.0005780847,0.00556959],"genre_scores_gemma":[0.5316405,0.0001264889,0.4637972,0.001326794,0.0003308123,0.0000334855,0.00001737979,0.0000465957,0.002680672],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8667058,"threshold_uncertainty_score":0.9998598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02403845612795377,"score_gpt":0.2559175215299839,"score_spread":0.2318790654020301,"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."}}