{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002800463,0.0002141289,0.0003100798,0.0003093854,0.0002184205,0.0002895956,0.00216602,0.0002356514,0.0002690794],"category_scores_gemma":[0.0006798728,0.0002241548,0.0002421385,0.000436608,0.000131483,0.0003239156,0.00234579,0.0001930601,0.0004354782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002003995,"about_ca_system_score_gemma":0.0001202038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000130941,"about_ca_topic_score_gemma":0.0001969501,"domain_scores_codex":[0.9977063,0.0002040379,0.0003623427,0.001193971,0.0002062549,0.00032707],"domain_scores_gemma":[0.9968842,0.00052166,0.0003401246,0.001741025,0.0003628249,0.0001502002],"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":[0.0009164715,0.0005738093,0.006517736,0.0007316328,0.0005302961,0.00008913401,0.002560357,0.4616949,0.00033378,0.2609752,0.225043,0.0400336],"study_design_scores_gemma":[0.0004993955,0.00005166003,0.001009186,0.00005260621,0.00009212558,7.924345e-7,0.0006343967,0.7045326,0.00009763027,0.2231734,0.06950891,0.0003472158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.146901,0.00001322338,0.8459634,0.0003563802,0.0005318396,0.0005952254,0.0001598336,0.0001022629,0.005376829],"genre_scores_gemma":[0.9867409,0.00005990901,0.002271497,0.0004258948,0.0002077025,0.000005777815,0.0001106787,0.00001792866,0.01015974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8436919,"threshold_uncertainty_score":0.9140766,"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."}}