{"id":"W7106856116","doi":"10.48448/pytr-n719","title":"Controllable Clustering with LLM-driven Embeddings","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Minnow Environmental (Canada)","funders":"","keywords":"Cluster analysis; Perspective (graphical); Embedding; Variety (cybernetics); Similarity (geometry); Conceptual clustering; Fuzzy clustering; Correlation 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001156487,0.001386274,0.0006192452,0.001033866,0.0007231609,0.001596684,0.0016104,0.001275935,0.006633263],"category_scores_gemma":[0.01236487,0.0005342687,0.0005605155,0.001196269,0.001146807,0.003479223,0.002708011,0.001738487,0.008624863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101149,"about_ca_system_score_gemma":0.001316693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002049659,"about_ca_topic_score_gemma":0.005485704,"domain_scores_codex":[0.9980007,0.0005540639,0.0001280136,0.0007922215,0.000410793,0.0001142599],"domain_scores_gemma":[0.9962001,0.00116993,0.0003120796,0.001364067,0.0008057121,0.0001480446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005868878,0.0002839909,0.00289064,0.0006380526,0.00006208567,0.000193106,0.0009769436,0.1392085,0.07217548,0.03780113,0.04447251,0.7007108],"study_design_scores_gemma":[0.0000561103,0.00009694362,0.0005747991,0.00004700574,0.00001526303,0.0001048819,0.0002691356,0.8767186,0.05735877,0.04425721,0.02044332,0.00005789573],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01706894,0.0002062546,0.9574177,0.000324245,0.0001079449,0.0001481108,0.001131893,0.01954894,0.004045889],"genre_scores_gemma":[0.2752188,0.0001555739,0.7054765,0.000466425,0.00007570186,0.0006021701,0.005517106,0.003799018,0.00868882],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006633263,"threshold_uncertainty_score":0.02219045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02247373254430754,"score_gpt":0.3039391017307841,"score_spread":0.2814653691864766,"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."}}