{"id":"W1633233002","doi":"10.48550/arxiv.1311.2334","title":"Embed and Conquer: Scalable Embeddings for Kernel k-Means on MapReduce","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Kernel (algebra); Computer science; Scalability; Embedding; Divide and conquer algorithms; Benchmark (surveying); Cluster analysis; Parallel computing; Computation; Scaling; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Discrete 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":[0.000280848,0.00041085,0.0004287216,0.0003153931,0.0002494604,0.0003258332,0.001911901,0.0003262865,0.00002698944],"category_scores_gemma":[0.00009718016,0.0004682876,0.0001481883,0.0003521637,0.0002093922,0.0005364201,0.002968273,0.0006837244,0.0001245561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003019203,"about_ca_system_score_gemma":0.0001677836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000188322,"about_ca_topic_score_gemma":0.00001018375,"domain_scores_codex":[0.9971691,0.00009134369,0.0002127126,0.001678277,0.0001627075,0.0006857978],"domain_scores_gemma":[0.9974591,0.0003369175,0.0001944636,0.0013534,0.0003197989,0.0003363426],"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":[0.0002088275,0.0003768542,0.000567681,0.0009316788,0.0003638149,0.0003496617,0.001188194,0.6336216,0.0008556097,0.3389729,0.005217866,0.01734525],"study_design_scores_gemma":[0.000785345,0.0001573892,0.0003138175,0.0001464902,0.0000211281,0.000007763651,0.00004914308,0.9434707,0.0004897062,0.05209306,0.001948678,0.0005167418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1762528,0.00004207333,0.8202155,0.0002650041,0.0004364355,0.0009025378,0.00003854292,0.0003168149,0.001530373],"genre_scores_gemma":[0.947983,0.0001783188,0.03854929,0.0001743926,0.00009612097,0.00001816303,0.00001792656,0.00005267221,0.01293017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7816662,"threshold_uncertainty_score":0.9997769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07124242219138041,"score_gpt":0.2299106971668386,"score_spread":0.1586682749754582,"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."}}