{"id":"W2008632807","doi":"10.1109/icde.2012.38","title":"Relevance Matters: Capitalizing on Less (Top-k Matching in Publish/Subscribe)","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Search engine indexing; Personalization; Cluster analysis; Tree (set theory); Data mining; Matching (statistics); Hierarchical clustering; Theoretical computer science; Information retrieval; Index (typography); Relevance (law); Machine learning; World Wide Web","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":[0.0005106286,0.0001293445,0.0001201958,0.0001926094,0.00006101796,0.000584235,0.001003851,0.00002991307,0.00003381718],"category_scores_gemma":[0.00001793154,0.0001142761,0.00003068635,0.0003629657,0.00001469763,0.005494445,0.000477469,0.0001356382,0.0003180539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004735816,"about_ca_system_score_gemma":0.000006787383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001823796,"about_ca_topic_score_gemma":0.0000291963,"domain_scores_codex":[0.9987143,0.00003844083,0.0001906057,0.0003056863,0.0002698058,0.0004811599],"domain_scores_gemma":[0.9992238,0.00006146893,0.00005089877,0.0005663922,0.00001334042,0.00008415719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003729532,0.0002542984,0.007376202,0.00004959994,0.00001517296,0.00003349944,0.002379171,0.000107366,0.0001656215,0.797789,0.05779736,0.1340289],"study_design_scores_gemma":[0.004866179,0.0003023477,0.117816,0.001035527,0.0000340536,0.00006851136,0.007879482,0.1107032,0.008541433,0.07730924,0.6664925,0.004951612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1453866,0.0002890505,0.7544375,0.01702027,0.003055078,0.0003889773,0.000004548676,0.0006754554,0.07874254],"genre_scores_gemma":[0.9278207,0.00002500586,0.06094582,0.007923127,0.0002214033,0.00001972735,0.00001225381,0.00001786917,0.003014032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7824342,"threshold_uncertainty_score":0.5633792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02835769156482166,"score_gpt":0.2513707586421479,"score_spread":0.2230130670773263,"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."}}