{"id":"W1979660621","doi":"10.1016/j.is.2007.03.001","title":"Indexing schemes for similarity search in datasets of short protein fragments","year":2007,"lang":"en","type":"article","venue":"Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Fonterra Co-Operative Group; Victoria University; Victoria University of Wellington; University of Ottawa","keywords":"Search engine indexing; Computer science; Nearest neighbor search; Similarity (geometry); Information retrieval; Data mining; 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":[0.005105868,0.0006075951,0.002320842,0.007284139,0.001580178,0.003121367,0.002649262,0.001734052,0.003113929],"category_scores_gemma":[0.02267348,0.0005423648,0.000907241,0.01209146,0.001234435,0.007279816,0.002940842,0.001442726,0.001891386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001600557,"about_ca_system_score_gemma":0.002648849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001577337,"about_ca_topic_score_gemma":0.002226989,"domain_scores_codex":[0.9959578,0.0007004474,0.0008705951,0.0005062127,0.001672982,0.0002919183],"domain_scores_gemma":[0.9848161,0.005748688,0.001153507,0.005606851,0.002229403,0.0004453892],"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":[0.002105981,0.0006163833,0.003774211,0.001163518,0.000166901,0.0001868382,0.000584535,0.02290793,0.03455627,0.0504809,0.01865593,0.8648006],"study_design_scores_gemma":[0.0008695814,0.00146746,0.005981797,0.0004083042,0.0004205077,0.002054705,0.0007453673,0.6664398,0.06069591,0.2287915,0.03183848,0.0002866446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1087223,0.0071375,0.8685054,0.0009641273,0.0005348951,0.0008764477,0.005114661,0.005632768,0.002511916],"genre_scores_gemma":[0.2606025,0.002541156,0.7215549,0.0002946273,0.0003373498,0.0008915524,0.01085145,0.0003488061,0.002577754],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007284139,"threshold_uncertainty_score":0.02700275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03226710671312223,"score_gpt":0.3096500319111106,"score_spread":0.2773829251979884,"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."}}