{"id":"W4406940792","doi":"10.1007/978-3-031-79029-4_29","title":"ERASMO: Leveraging Large Language Models for Enhanced Clustering Segmentation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Cluster analysis; Segmentation; Artificial intelligence; Natural language processing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001514965,0.002339049,0.001887186,0.003071434,0.001280557,0.003085922,0.003242587,0.002641829,0.01025753],"category_scores_gemma":[0.003709154,0.001362043,0.00277848,0.003103648,0.0005895453,0.00343906,0.002789836,0.002857481,0.01669591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009235131,"about_ca_system_score_gemma":0.001560178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01126077,"about_ca_topic_score_gemma":0.02677387,"domain_scores_codex":[0.9985445,0.0003325635,0.00007664082,0.0005462338,0.0003325609,0.0001675192],"domain_scores_gemma":[0.9982622,0.0007589298,0.00007612941,0.0004309164,0.0003647165,0.0001070274],"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":[0.0008859092,0.0003796588,0.001267825,0.00036971,0.0004501864,0.0003483383,0.0003962277,0.06449161,0.05448545,0.006560282,0.06095131,0.8094134],"study_design_scores_gemma":[0.00004923721,0.00008137764,0.0005101349,0.0000260455,0.00009481168,0.0002113503,0.0001159359,0.9520457,0.02084254,0.01240308,0.01355696,0.00006269186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01062502,0.0009050617,0.925997,0.000240595,0.0002921925,0.0001547579,0.002380287,0.05673909,0.002666],"genre_scores_gemma":[0.09535728,0.0006004477,0.8671213,0.0005546293,0.0002696934,0.0003529179,0.01380935,0.009489469,0.01244495],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01126077,"threshold_uncertainty_score":0.03431481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02086979178953022,"score_gpt":0.2726274240281408,"score_spread":0.2517576322386106,"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."}}