{"id":"W1596527724","doi":"10.1007/978-3-540-24571-1_73","title":"Similarity Search and Dimensionality Reduction: Not All Dimensions Are Equally Useful","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Dimensionality reduction; Search engine indexing; Computer science; Curse of dimensionality; Reduction (mathematics); Speedup; Nearest neighbor search; Similarity (geometry); Overhead (engineering); Diffusion map; Space (punctuation); Range query (database); Range (aeronautics); Process (computing); Similitude; Data mining; Algorithm; Theoretical computer science; Nonlinear dimensionality reduction; Artificial intelligence; Mathematics; Information retrieval; Search engine; Parallel computing; Web search query","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":[0.001111989,0.0007648271,0.001669349,0.001382745,0.0008229684,0.003183609,0.0007825665,0.001015121,0.005935682],"category_scores_gemma":[0.00725139,0.0004119983,0.0007196001,0.004253793,0.001820969,0.006664381,0.002060079,0.001704613,0.002840241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005423119,"about_ca_system_score_gemma":0.0008327461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00072589,"about_ca_topic_score_gemma":0.0008710494,"domain_scores_codex":[0.9984163,0.0004362591,0.0001147472,0.0002450847,0.0007231854,0.00006449567],"domain_scores_gemma":[0.997691,0.0009843785,0.0001541467,0.000671202,0.0004121164,0.00008718586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009622244,0.00005989916,0.0009573297,0.0006957785,0.0001302572,0.00008749563,0.0003415146,0.004464257,0.003400574,0.1993135,0.05726461,0.7331886],"study_design_scores_gemma":[0.00003243571,0.000176847,0.001858264,0.0002961427,0.0001492891,0.001280092,0.0004865696,0.04318262,0.005227493,0.8257591,0.121465,0.00008618185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02844345,0.05286392,0.8274187,0.01747169,0.002516205,0.0001280306,0.0007928833,0.001210354,0.06915484],"genre_scores_gemma":[0.3020325,0.04441584,0.5988138,0.003262569,0.003626733,0.0003380448,0.00133371,0.0004701127,0.04570672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005935682,"threshold_uncertainty_score":0.01985681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04871447997598213,"score_gpt":0.2780690114544754,"score_spread":0.2293545314784933,"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."}}