{"id":"W2897914812","doi":"10.48550/arxiv.1810.04361","title":"Semi-supervised clustering for de-duplication","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Oracle; Correlation clustering; Computer science; Graph; Cluster (spacecraft); Combinatorics; Complete-linkage clustering; Data mining; Mathematics; Theoretical computer science; Pattern recognition (psychology); CURE data clustering algorithm; Artificial intelligence","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":[0.005017576,0.001906656,0.004056778,0.002885619,0.002293746,0.002182032,0.006315376,0.004064401,0.003244655],"category_scores_gemma":[0.01931199,0.00144226,0.002447371,0.004285082,0.003167853,0.005378317,0.003666089,0.004119574,0.002207171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003668165,"about_ca_system_score_gemma":0.002840881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004741231,"about_ca_topic_score_gemma":0.006775467,"domain_scores_codex":[0.9923652,0.002257983,0.0003973205,0.002831905,0.001769435,0.0003781365],"domain_scores_gemma":[0.983067,0.006872488,0.001913469,0.005270025,0.002401299,0.0004756018],"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":[0.0006751817,0.0003973084,0.004377104,0.001034761,0.0006085503,0.0004057749,0.0008592934,0.6955331,0.005487765,0.06856941,0.0347449,0.1873068],"study_design_scores_gemma":[0.00002971874,0.00006552508,0.0006174213,0.00003866861,0.00003212767,0.0001603573,0.000100806,0.919986,0.001698461,0.07345977,0.003775719,0.0000354392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02016241,0.001311676,0.9720228,0.001061135,0.0001120647,0.0002028218,0.001059612,0.001916101,0.002151296],"genre_scores_gemma":[0.4432475,0.001246442,0.5369131,0.00116598,0.0004721125,0.000631401,0.008164669,0.0009639788,0.007194752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006315376,"threshold_uncertainty_score":0.02661449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3552284649169554,"score_gpt":0.3098680257081865,"score_spread":0.04536043920876892,"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."}}