{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009515497,0.00006053216,0.0001611243,0.0002371146,0.00005401742,0.00008203583,0.0007048852,0.0000188885,0.00001403954],"category_scores_gemma":[0.00003789335,0.00005212835,0.0001123677,0.001427947,0.00002543426,0.0003582327,0.0001708424,0.00003777748,8.854437e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002297328,"about_ca_system_score_gemma":0.00003048931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006019723,"about_ca_topic_score_gemma":0.00003242587,"domain_scores_codex":[0.9992549,0.00003808095,0.0001481573,0.0002511542,0.0001487762,0.0001589776],"domain_scores_gemma":[0.9992374,0.0001420916,0.00003933842,0.0004792178,0.00006571012,0.00003623111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009934551,0.0001869915,0.002932357,0.00006736068,0.0004874279,0.000002175742,0.0001878327,0.02538721,0.0003875498,0.6149488,0.000105726,0.3552966],"study_design_scores_gemma":[0.0002938109,0.00002728666,0.002638638,0.000004101122,0.00007795852,2.157885e-8,0.00001320907,0.9840521,0.006123294,0.004091101,0.002593585,0.00008490112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002711967,0.0000144858,0.9976083,0.0006397172,0.00004527785,0.000113954,0.00001107679,0.00004974403,0.001246232],"genre_scores_gemma":[0.1037151,0.000001358394,0.8958827,0.0002091472,0.000007078881,0.000006764177,0.00001628754,0.000002257156,0.0001592846],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9586649,"threshold_uncertainty_score":0.2125732,"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."}}