{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001439855,0.0005573078,0.0005365164,0.0006318092,0.0005060216,0.0008978898,0.002613651,0.0002818453,0.00003157844],"category_scores_gemma":[0.00006630099,0.0005118865,0.000110105,0.0005393651,0.001000409,0.001270086,0.004411974,0.001015875,0.00004120488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002952849,"about_ca_system_score_gemma":0.0004120767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006434696,"about_ca_topic_score_gemma":0.00005768525,"domain_scores_codex":[0.9950077,0.0000586896,0.0005059447,0.002162285,0.001519842,0.0007455464],"domain_scores_gemma":[0.997215,0.0002468446,0.0002027021,0.001764034,0.0002783024,0.0002931105],"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":[0.00003394351,0.0003114746,0.0002084532,0.0002844385,0.0001343814,0.0009878718,0.001839465,0.06476305,0.0006356178,0.4296053,0.0004609526,0.500735],"study_design_scores_gemma":[0.001525283,0.0006194789,0.003751037,0.001407254,0.00007080763,0.0003574809,0.00000215847,0.3284293,0.00283771,0.6510032,0.007003482,0.002992732],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004461303,0.0003660813,0.9900997,0.005683007,0.001760436,0.0004703898,0.00002759952,0.0002060187,0.0009406871],"genre_scores_gemma":[0.2760356,0.0002699987,0.7170579,0.004437226,0.0009218008,0.00001329823,0.00005317898,0.00006536516,0.001145554],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4977423,"threshold_uncertainty_score":0.9997333,"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."}}