{"id":"W4323896842","doi":"10.1109/tbdata.2023.3255003","title":"Approximate Clustering Ensemble Method for Big Data","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Disjoint sets; Big data; Correlation clustering; Data mining; Component (thermodynamics); Cluster (spacecraft); Artificial intelligence; Mathematics; Combinatorics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00227493,0.001239838,0.00194772,0.002016157,0.001166332,0.001660384,0.002868558,0.001327409,0.002977135],"category_scores_gemma":[0.0063682,0.0004746531,0.001542984,0.00296577,0.0006738655,0.002885309,0.00205053,0.002151108,0.001491634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001326416,"about_ca_system_score_gemma":0.001471115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006591692,"about_ca_topic_score_gemma":0.006989103,"domain_scores_codex":[0.9977398,0.0005044582,0.0001005164,0.0005604505,0.0009542068,0.000140581],"domain_scores_gemma":[0.9975706,0.0006663449,0.0001733341,0.0006122164,0.00084851,0.0001289646],"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":[0.000228738,0.00008809231,0.002033981,0.000203608,0.000319671,0.0001389635,0.0001859749,0.705265,0.00422882,0.04704318,0.01102599,0.2292379],"study_design_scores_gemma":[0.000005956249,0.00001322584,0.0001810711,0.000005652746,0.000012451,0.00002135897,0.00001700202,0.9845483,0.0007616364,0.01234341,0.002080575,0.000009413166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003119697,0.0003664529,0.9942153,0.000123945,0.0000798064,0.00004489962,0.0001383505,0.0009362323,0.000975332],"genre_scores_gemma":[0.2161585,0.0008298415,0.7743323,0.0003058753,0.0003616745,0.0004719201,0.00200196,0.0005813942,0.004956465],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006591692,"threshold_uncertainty_score":0.01310664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3223194882196442,"score_gpt":0.4085578238677204,"score_spread":0.08623833564807626,"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."}}