{"id":"W2086959852","doi":"10.1007/s10994-009-5103-0","title":"NP-hardness of Euclidean sum-of-squares clustering","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":863,"is_retracted":false,"has_abstract":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal; Polytechnique Montréal","funders":"","keywords":"Cluster analysis; Mathematics; Euclidean distance; Explained sum of squares; Euclidean geometry; Combinatorics; Pattern recognition (psychology); Artificial intelligence; Computer science; Statistics","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":[0.002537121,0.001411517,0.003681193,0.001009609,0.002140614,0.004627993,0.005001582,0.003719729,0.007659008],"category_scores_gemma":[0.02615032,0.001245204,0.0015418,0.003963928,0.003144532,0.008856873,0.003722825,0.005054315,0.001836969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003060328,"about_ca_system_score_gemma":0.003614254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005403852,"about_ca_topic_score_gemma":0.005508895,"domain_scores_codex":[0.9941329,0.001996443,0.0003830916,0.001290274,0.001659982,0.0005372186],"domain_scores_gemma":[0.9765046,0.01788844,0.000920865,0.002771514,0.001392822,0.0005217586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001748311,0.0004490148,0.002109059,0.001522197,0.0003359361,0.0003847281,0.0008351782,0.5310929,0.003592115,0.171881,0.08371957,0.2023299],"study_design_scores_gemma":[0.0002152641,0.00005834208,0.0004743753,0.00005793379,0.00004826103,0.0002916596,0.0002854683,0.526195,0.001816831,0.4641044,0.006420189,0.00003229407],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09082035,0.005213303,0.8392804,0.01782815,0.0007786136,0.0003265899,0.004386668,0.002989387,0.03837655],"genre_scores_gemma":[0.6302361,0.002875429,0.3351007,0.002868867,0.0009604881,0.0007316512,0.005392831,0.001430299,0.02040365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007659008,"threshold_uncertainty_score":0.02562195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01257153537582592,"score_gpt":0.2570000966085654,"score_spread":0.2444285612327395,"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."}}