{"id":"W4413360655","doi":"10.1109/icde65448.2025.00101","title":"A Length Enhanced B<sup>+</sup>-Tree Based Index for Efficient Set Similarity Query","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Computer science; Set (abstract data type); Index (typography); Similarity (geometry); Tree (set theory); Algorithm; Mathematics; Combinatorics; 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":[0.001569572,0.0006241876,0.001444299,0.002829723,0.0011119,0.002178404,0.002596071,0.001118453,0.005070867],"category_scores_gemma":[0.007698735,0.0004939321,0.0007123235,0.004902532,0.0006918692,0.006660089,0.004520524,0.001290538,0.003613035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001736418,"about_ca_system_score_gemma":0.003154174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00342073,"about_ca_topic_score_gemma":0.004839458,"domain_scores_codex":[0.9979591,0.0002433342,0.0003080209,0.0003096905,0.0009845368,0.000195307],"domain_scores_gemma":[0.996877,0.0007764135,0.00025548,0.001100517,0.0007588096,0.000231796],"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":[0.001414235,0.0006190008,0.003697234,0.0006858977,0.0001043936,0.0003155619,0.0006416781,0.02615874,0.06670946,0.0915295,0.06898539,0.7391389],"study_design_scores_gemma":[0.0003346157,0.0007388804,0.001757326,0.0001105511,0.00008950662,0.001204344,0.0003631894,0.771655,0.0465267,0.09028463,0.08676544,0.0001697166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02779039,0.001084345,0.9518438,0.0007039443,0.0001691487,0.0005920122,0.002689744,0.008367223,0.006759312],"genre_scores_gemma":[0.1382872,0.0004800061,0.8500763,0.0004851183,0.000130781,0.0004610424,0.005100931,0.0004430863,0.004535514],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005070867,"threshold_uncertainty_score":0.01696372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01608985870247986,"score_gpt":0.2646229309902215,"score_spread":0.2485330722877417,"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."}}