{"id":"W3003706366","doi":"10.1007/978-3-030-51310-8_10","title":"Enhancement of Short Text Clustering by Iterative Classification","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; CURE data clustering algorithm; Pattern recognition (psychology); Correlation clustering; Computer science; Single-linkage clustering; Outlier; Artificial intelligence; Canopy clustering algorithm; Data mining; Hierarchical clustering","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":[0.0004095982,0.0002681242,0.0003284982,0.0002672637,0.000143902,0.0003184149,0.002530378,0.0001618054,0.00000539035],"category_scores_gemma":[0.00003841922,0.0002607965,0.00008532619,0.001327305,0.000279051,0.0002942075,0.00250251,0.0005438286,0.000005357556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002104501,"about_ca_system_score_gemma":0.0002457025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003485602,"about_ca_topic_score_gemma":0.00001045445,"domain_scores_codex":[0.9973536,0.0000557587,0.0005282643,0.001241649,0.0005187202,0.0003020513],"domain_scores_gemma":[0.9982542,0.0001088581,0.0002576392,0.00107252,0.0002043323,0.000102421],"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":[0.000004792601,0.0001259368,0.0002109544,0.00008983101,0.00001114095,0.000002377804,0.001816895,0.01461295,0.1172182,0.001278072,0.0001102393,0.8645186],"study_design_scores_gemma":[0.00004102692,0.00008417758,0.0003133944,0.00008609115,0.000002466223,0.000002763045,5.689473e-7,0.760334,0.2303979,0.008401724,0.0001256108,0.0002103541],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003696023,0.0001129103,0.9928957,0.002100757,0.0004123544,0.0005377645,0.000007665535,0.0001682452,0.00006861635],"genre_scores_gemma":[0.6125999,0.00002571508,0.3869051,0.0003236539,0.00005691784,0.00007635384,0.00000545138,0.000006016673,8.921083e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8643083,"threshold_uncertainty_score":0.9999844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02989990342643889,"score_gpt":0.295199108661411,"score_spread":0.2652992052349721,"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."}}