{"id":"W4416703099","doi":"10.1016/j.datak.2025.102536","title":"Enhancing clustering stability, compactness, and separation in multimodal data environments","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministério da Ciência, Tecnologia, Inovações e Comunicações","keywords":"Cluster analysis; Benchmark (surveying); Stability (learning theory); Rand index; Hierarchical clustering; Benchmarking; Consensus clustering; Embedding; Focus (optics); Core (optical fiber)","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":[],"consensus_categories":[],"category_scores_codex":[0.0004998313,0.000156044,0.0001720022,0.0002600007,0.00007124728,0.0002055019,0.0004947414,0.00004618675,0.00002953865],"category_scores_gemma":[0.0001251851,0.0001754185,0.000009498923,0.000311637,0.00001791853,0.002421553,0.002314056,0.0001318834,0.00004269436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006556023,"about_ca_system_score_gemma":0.00001346445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002576304,"about_ca_topic_score_gemma":0.001834802,"domain_scores_codex":[0.9989544,0.000008124009,0.0002826005,0.000450542,0.00009604168,0.0002083166],"domain_scores_gemma":[0.9991596,0.00005835957,0.00004900678,0.0007104885,0.0000111057,0.00001141279],"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":[0.0002248982,0.001299776,0.2421634,0.00756282,0.0003123824,0.00003912872,0.002304158,0.004898496,0.2570936,0.003214458,0.00619777,0.4746891],"study_design_scores_gemma":[0.0005348607,0.000001281257,0.03406961,0.0001309237,0.00002498059,4.439456e-7,0.0001647066,0.9514252,0.0003284507,0.00001485177,0.01314046,0.0001642332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7616834,0.00133567,0.2300985,0.000220844,0.001510829,0.0008047404,0.0001417373,0.0002340132,0.003970316],"genre_scores_gemma":[0.9960979,0.00002436364,0.00136379,0.00005434073,0.0002279899,0.00000870134,0.002158566,0.00001733689,0.00004697362],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9465267,"threshold_uncertainty_score":0.715336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04420924631857913,"score_gpt":0.2996458049990858,"score_spread":0.2554365586805067,"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."}}