{"id":"W2950930770","doi":"10.48550/arxiv.cs/0211018","title":"Indexing schemes for similarity search: an illustrated paradigm","year":2002,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Marsden Fund; Fonterra Co-Operative Group; Natural Sciences and Engineering Research Council of Canada; Royal Society Te Apārangi; Royal Society; University of Ottawa","keywords":"Search engine indexing; Similarity (geometry); Nearest neighbor search; Metric (unit); Measure (data warehouse); Similarity measure; Computer science; Variety (cybernetics); Index (typography); Data mining; Information retrieval; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00821635,0.0007244114,0.001373431,0.004317481,0.002062656,0.006776693,0.003781019,0.002725072,0.004437185],"category_scores_gemma":[0.02494384,0.000658587,0.001710769,0.008285636,0.00651505,0.01967313,0.008033901,0.003677398,0.001876823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002285602,"about_ca_system_score_gemma":0.00141595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009366031,"about_ca_topic_score_gemma":0.0005635792,"domain_scores_codex":[0.9923495,0.003183492,0.0009496252,0.000904196,0.002271066,0.0003421683],"domain_scores_gemma":[0.9870913,0.005063966,0.0006612423,0.005546884,0.001169509,0.0004671187],"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":[0.00003043315,0.000021728,0.0001974116,0.00005723432,0.000009392865,0.00004388153,0.0001694374,0.003182272,0.0008357622,0.9763353,0.001085345,0.01803169],"study_design_scores_gemma":[0.00002435146,0.00006633979,0.0001139414,0.00003026048,0.000009549892,0.0002119182,0.00009154149,0.04564822,0.001152289,0.9404424,0.01218351,0.00002565559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005578014,0.0006259215,0.9889804,0.001413158,0.00008650952,0.000139274,0.0001677915,0.0001710905,0.002837883],"genre_scores_gemma":[0.1529739,0.001627091,0.8404028,0.0005088667,0.0003845533,0.0006031924,0.0004351117,0.0001252227,0.002939245],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00821635,"threshold_uncertainty_score":0.04345274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2419410930848392,"score_gpt":0.2253713893522944,"score_spread":0.01656970373254479,"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."}}