{"id":"W4392197543","doi":"10.28924/2291-8639-22-2024-36","title":"Impact of Dataset Scaling on Hierarchical Clustering: A Comparative Analysis of Distance-Based and Ratio-Based Methods","year":2024,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hierarchical clustering; Mathematics; Cluster analysis; Scaling; Multidimensional scaling; Data mining; Statistics; Computer science; Geometry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006403553,0.0001078545,0.0004480263,0.001679234,0.00004701576,0.0001491091,0.0005227072,0.00002964089,0.00001461514],"category_scores_gemma":[0.00004292718,0.00008288149,0.0003310866,0.002114389,0.0001387837,0.0001882356,0.0001022966,0.0001707327,2.673112e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007659424,"about_ca_system_score_gemma":0.0001266594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004308017,"about_ca_topic_score_gemma":0.00001985491,"domain_scores_codex":[0.9984685,0.0001328089,0.0005661257,0.0002447151,0.0004906732,0.00009719146],"domain_scores_gemma":[0.9979972,0.0008876648,0.0003212359,0.0002616967,0.0004291825,0.0001030187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002169664,0.0004225813,0.004547348,0.00004654947,0.01722763,0.00001699026,0.0004782761,0.8256523,0.006033589,0.01249787,0.00005396272,0.1328059],"study_design_scores_gemma":[0.0002015689,0.0001306978,0.01153094,0.00003774221,0.0007416566,0.000003490413,0.00001867391,0.9853835,0.001133063,0.0003979387,0.0003514818,0.00006928622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01915324,0.0001893609,0.9796399,0.0003892033,0.00001894942,0.00006635984,0.0005151662,0.00000665151,0.00002120462],"genre_scores_gemma":[0.8616068,0.0000336005,0.1381777,0.00002043745,0.00002918445,0.000008746221,0.0001167139,0.0000029618,0.000003872843],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8424535,"threshold_uncertainty_score":0.3379809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0474050211507275,"score_gpt":0.4728101699367248,"score_spread":0.4254051487859973,"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."}}