{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03860232,0.001477423,0.001659472,0.007135326,0.001633875,0.003222826,0.002218499,0.001187663,0.001279744],"category_scores_gemma":[0.1319438,0.000371355,0.001702856,0.008904997,0.001107569,0.004575285,0.002577697,0.001070226,0.0005867872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542274,"about_ca_system_score_gemma":0.002061511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004750734,"about_ca_topic_score_gemma":0.005230637,"domain_scores_codex":[0.9632388,0.02151409,0.002302068,0.002815936,0.009686881,0.0004421653],"domain_scores_gemma":[0.8957323,0.07627199,0.004961959,0.008020543,0.01424458,0.0007686123],"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":[0.002069269,0.0005568943,0.04401766,0.004310182,0.002543677,0.0003102353,0.003609227,0.09808402,0.006658649,0.02010697,0.007700441,0.8100328],"study_design_scores_gemma":[0.0004145967,0.00249014,0.06536499,0.001339285,0.001809668,0.001240508,0.007975265,0.8422154,0.01596943,0.03343921,0.02727131,0.0004702645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3538649,0.02242121,0.6042799,0.00159417,0.000796375,0.001454131,0.001068193,0.002458446,0.01206263],"genre_scores_gemma":[0.5563169,0.00350414,0.4369371,0.000194554,0.000164442,0.0004565852,0.00127064,0.0004539155,0.0007016733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03860232,"threshold_uncertainty_score":0.204151,"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."}}