{"id":"W4281975883","doi":"10.1145/3805034","title":"Streaming Hierarchical Clustering Based on Point-Set Kernel","year":2022,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"State Key Laboratory of Novel Software Technology; Nanjing University; National Natural Science Foundation of China","keywords":"Hierarchical clustering; Cluster analysis; Computer science; Data mining; Single-linkage clustering; Brown clustering; Tree (set theory); Consensus clustering; Correlation clustering; Hierarchical clustering of networks; CURE data clustering algorithm; Scalability; Kernel (algebra); Tree structure; Constrained clustering; Artificial intelligence; Mathematics; Algorithm; Database; Binary tree","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","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007092744,0.0008046355,0.0007222937,0.0007342101,0.0007524445,0.001117058,0.01522384,0.0003299337,0.000393725],"category_scores_gemma":[0.0002906745,0.0008637097,0.0003108354,0.0007103118,0.0001758883,0.001713101,0.00629926,0.00396715,0.0001945419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008173398,"about_ca_system_score_gemma":0.0008914137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004457181,"about_ca_topic_score_gemma":0.0004940313,"domain_scores_codex":[0.9931852,0.0006159127,0.0007285065,0.003324496,0.001233428,0.0009125199],"domain_scores_gemma":[0.9829966,0.002226344,0.0002171419,0.01414024,0.00008985901,0.0003297417],"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":[0.0004006421,0.002230526,0.00003715876,0.0003497511,0.000398753,0.0002804665,0.001278355,0.5905523,0.0001699149,0.0001393632,0.001121284,0.4030415],"study_design_scores_gemma":[0.001050946,0.0002630032,0.0003210722,0.0005240484,0.00005774086,0.000007303931,0.0001385141,0.9884937,0.0003341281,0.003422421,0.004437756,0.0009493302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001267902,0.0001813542,0.9770254,0.001266308,0.002964635,0.0006946734,0.01534648,0.0005050921,0.000748189],"genre_scores_gemma":[0.6189705,0.0003504675,0.3603444,0.00067187,0.0008721789,0.0009623643,0.01391086,0.000383747,0.003533704],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6177025,"threshold_uncertainty_score":0.9999199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07734526681048454,"score_gpt":0.3535982704819712,"score_spread":0.2762530036714866,"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."}}