{"id":"W1986114210","doi":"10.1016/j.csda.2008.08.001","title":"Finding approximate solutions to combinatorial problems with very large data sets using BIRCH","year":2008,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"TRIUMF","keywords":"Outlier; Estimator; Computer science; Algorithm; Robustness (evolution); Covariance; Mathematical optimization; Mathematics; Statistics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001016531,0.0002834765,0.0006235384,0.0003367182,0.0008240616,0.00009632431,0.000933934,0.00006623077,0.0000778871],"category_scores_gemma":[0.001542711,0.00026391,0.00004396367,0.001381604,0.0001365607,0.000444732,0.001277459,0.0002229758,0.0000137924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001128186,"about_ca_system_score_gemma":0.0002524819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001427725,"about_ca_topic_score_gemma":0.0001796524,"domain_scores_codex":[0.996783,0.0002140936,0.000643008,0.0009653191,0.0008376685,0.0005569145],"domain_scores_gemma":[0.9953715,0.002131385,0.0002794247,0.001564154,0.0003895332,0.0002639816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007551771,0.0006225843,0.001975744,0.0001575238,0.002011425,0.0001192222,0.0004192952,0.3097365,0.00001135495,0.6754488,0.007744585,0.001677422],"study_design_scores_gemma":[0.0004241771,0.00003388548,0.0005437118,0.0000230242,0.001095083,0.00001478667,0.0000174578,0.6862921,5.956283e-7,0.3108302,0.0004721654,0.0002529146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001913545,0.00003140637,0.9472151,0.0000501853,0.0001096987,0.0003318201,0.05024229,0.0000681506,0.00003778793],"genre_scores_gemma":[0.06248507,0.00001343302,0.916663,0.00006017542,0.00007353479,0.00001258077,0.02062679,0.00004241328,0.00002300002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3765555,"threshold_uncertainty_score":0.9999813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3862878097668099,"score_gpt":0.463281868573303,"score_spread":0.07699405880649307,"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."}}