{"id":"W2208773343","doi":"10.48550/arxiv.1506.05900","title":"Representation Learning for Clustering: A Statistical Framework","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Dimension (graph theory); Correlation clustering; Representation (politics); Artificial intelligence; Clustering high-dimensional data; Sample (material); Conceptual clustering; Theoretical computer science; Constrained clustering; Class (philosophy); Data mining; CURE data clustering algorithm; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004389278,0.0002358157,0.0003076267,0.0001596287,0.0001865948,0.0002131989,0.001031862,0.0002718104,0.00001881947],"category_scores_gemma":[0.0005964315,0.0002752722,0.0001333024,0.0003410706,0.00005771638,0.0001875478,0.00144065,0.0009936854,0.00004888673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001311456,"about_ca_system_score_gemma":0.0001667148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001306911,"about_ca_topic_score_gemma":0.000007307745,"domain_scores_codex":[0.9981245,0.0002396495,0.0001790275,0.001018427,0.0001108199,0.0003275327],"domain_scores_gemma":[0.9981759,0.0004712151,0.0002229902,0.0007209427,0.0002084462,0.0002005705],"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":[0.00003324642,0.00003707632,0.001351348,0.00007120958,0.0000462848,0.00008945985,0.0004476894,0.8415327,0.000001861379,0.1492691,0.0007193561,0.006400657],"study_design_scores_gemma":[0.0002852747,0.00008574084,0.0003225479,0.00006094192,0.00002971105,0.000003586731,0.00005969911,0.8520308,0.000004681186,0.1452651,0.001585966,0.000265905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007820884,0.00002729321,0.9893726,0.0001779812,0.0007883261,0.0002739948,0.000009774255,0.0003762299,0.00115291],"genre_scores_gemma":[0.8720914,0.00002046472,0.1249332,0.00005404936,0.0002310845,0.000002979247,0.00005878092,0.00002207176,0.002585992],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8644394,"threshold_uncertainty_score":0.99997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.10326938999633,"score_gpt":0.2558038470310963,"score_spread":0.1525344570347663,"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."}}