{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01671179,0.001548541,0.002011409,0.00363604,0.00207993,0.006774498,0.005916583,0.004581178,0.004583616],"category_scores_gemma":[0.07684788,0.001312181,0.002384795,0.004127916,0.0108825,0.01504242,0.007204793,0.007468094,0.00123126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005107939,"about_ca_system_score_gemma":0.003438016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002230736,"about_ca_topic_score_gemma":0.00139619,"domain_scores_codex":[0.9803172,0.01188422,0.000731383,0.003032296,0.003321876,0.0007131227],"domain_scores_gemma":[0.9166541,0.06223099,0.004906902,0.01190256,0.003251588,0.001053845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002384968,0.00003105561,0.0002820306,0.0000983542,0.0000464138,0.00003692217,0.0001577516,0.04077638,0.0003959369,0.9459715,0.0009201662,0.01125965],"study_design_scores_gemma":[0.00001000723,0.00002306224,0.00009217157,0.00002550881,0.00001094929,0.00003427146,0.00003336829,0.195168,0.0003866428,0.8023961,0.001800748,0.0000191003],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001714703,0.0001859337,0.995635,0.0009423591,0.0000232946,0.0000353218,0.00006852615,0.00009992256,0.001295021],"genre_scores_gemma":[0.316254,0.001566748,0.6731285,0.001461696,0.0009233506,0.001226474,0.0007230141,0.0003935048,0.004322634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01671179,"threshold_uncertainty_score":0.08838141,"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."}}