{"id":"W2139676742","doi":"10.48550/arxiv.1307.2669","title":"Text Categorization via Similarity Search: An Efficient and Effective Novel Algorithm","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Similarity (geometry); Centroid; Cluster analysis; Categorization; Artificial intelligence; Outlier; Preprocessor; Metric (unit); Text categorization; Class (philosophy); Point (geometry); Similarity measure; Measure (data warehouse); Nearest neighbor search; Pattern recognition (psychology); Data mining; Mathematics; Image (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":[0.0002607125,0.0002974916,0.0002617723,0.0003644512,0.0002367541,0.0003027915,0.001342067,0.0003738699,0.00001486742],"category_scores_gemma":[0.00002959251,0.0003193265,0.00007493717,0.0005755513,0.0002345092,0.0005544542,0.002104305,0.0005286679,0.00005614454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001656376,"about_ca_system_score_gemma":0.00008802852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002790762,"about_ca_topic_score_gemma":0.000007553469,"domain_scores_codex":[0.9980388,0.0001215243,0.000166177,0.001222885,0.0001307214,0.0003198379],"domain_scores_gemma":[0.9981589,0.0001020024,0.0001808546,0.001155577,0.0002405871,0.0001620472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001421921,0.0005834028,0.001362924,0.0001032504,0.0001053857,0.00003979995,0.0009300819,0.1171248,0.0007641576,0.7647244,0.00009033735,0.1141573],"study_design_scores_gemma":[0.0003565419,0.00008750249,0.007721097,0.00001819678,0.00002451041,0.000003068071,0.0001146027,0.9709426,0.001290406,0.01892639,0.0001496218,0.0003655237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1581431,0.00002702138,0.8398963,0.0001904637,0.0002367595,0.0006192963,0.00001183442,0.0005907089,0.0002845058],"genre_scores_gemma":[0.9865844,0.00007460447,0.01295093,0.00003906468,0.00003001381,0.000006236582,0.00003107412,0.00001371611,0.0002699546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8538178,"threshold_uncertainty_score":0.9999259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06421189842904142,"score_gpt":0.202638992897949,"score_spread":0.1384270944689076,"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."}}