{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001429651,0.0002331296,0.0002544517,0.0004070628,0.0004559345,0.0002868849,0.006426649,0.00009541919,0.000003650064],"category_scores_gemma":[0.00006414986,0.0002347065,0.00005186991,0.001341236,0.00004932781,0.001113909,0.0003728573,0.0003228488,0.0001714857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006424345,"about_ca_system_score_gemma":0.0001350941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007104708,"about_ca_topic_score_gemma":0.0002380031,"domain_scores_codex":[0.9968954,0.0001162989,0.0003259526,0.001427958,0.000523428,0.0007109929],"domain_scores_gemma":[0.9923183,0.0006626186,0.00006787103,0.006692615,0.00008279897,0.0001758289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002702832,0.00006260298,1.361817e-7,0.00007701516,0.00004479896,0.00001632959,0.00009016671,0.01902181,0.003919291,0.00002023402,0.002516015,0.9742046],"study_design_scores_gemma":[0.0005331994,0.00007432282,0.000004529643,0.00003979753,0.00001456356,0.00003089647,0.00002622825,0.9536978,0.007975087,0.0003906713,0.03695963,0.000253297],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002713191,0.00002267105,0.9919521,0.001029203,0.003474093,0.000504819,0.002174979,0.0007284301,0.00008653119],"genre_scores_gemma":[0.0125123,0.0002168741,0.9835083,0.0001917435,0.0006189556,0.0002041873,0.0006056842,0.0000852044,0.002056726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9739513,"threshold_uncertainty_score":0.9989491,"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."}}