{"id":"W2104992338","doi":"10.1109/ccece.2004.1347728","title":"Analysis of distance based indexing methods for similarity search","year":2004,"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 Waterloo","funders":"","keywords":"Search engine indexing; Computer science; Similarity (geometry); Nearest neighbor search; Metric (unit); Data mining; Database index; Metric space; Tree (set theory); Access method; Data structure; Similitude; Space (punctuation); Tree structure; Information retrieval; Artificial intelligence; Mathematics; Database","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":[0.00670022,0.0007929992,0.001396428,0.006617634,0.0009804019,0.002462731,0.002466911,0.001265313,0.005269888],"category_scores_gemma":[0.04212311,0.0003900442,0.0009041434,0.008138004,0.001148184,0.007405208,0.00170227,0.001158218,0.001706442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002230961,"about_ca_system_score_gemma":0.001292199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001346639,"about_ca_topic_score_gemma":0.001080136,"domain_scores_codex":[0.9862098,0.003322991,0.0008374563,0.0008369234,0.008437256,0.0003555729],"domain_scores_gemma":[0.964567,0.02584533,0.001229988,0.003372347,0.004660819,0.0003245305],"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":[0.0006150497,0.0003721913,0.004040615,0.001015809,0.0001921099,0.00007901598,0.0003968252,0.0549073,0.009931329,0.1981114,0.005387255,0.7249512],"study_design_scores_gemma":[0.0001708648,0.0006117194,0.002914505,0.0001329127,0.0001073732,0.0007708254,0.0003211691,0.8216965,0.02015561,0.1330057,0.02001195,0.0001008285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03423089,0.007271596,0.9504037,0.0005022324,0.0001296268,0.0002579939,0.0003027548,0.000813473,0.00608771],"genre_scores_gemma":[0.3035454,0.003442659,0.6864513,0.0001774174,0.0003395211,0.0005577704,0.001491044,0.0003184272,0.003676411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00670022,"threshold_uncertainty_score":0.03543454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05438294394552019,"score_gpt":0.3891997797608845,"score_spread":0.3348168358153643,"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."}}