{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001629282,0.00006634968,0.0001202761,0.0002009966,0.00005410266,0.0001083002,0.0004350658,0.00006054548,0.000001017926],"category_scores_gemma":[0.00004273279,0.00005857675,0.0000184231,0.0002423091,0.0000120942,0.002729726,0.0001961914,0.00007787595,0.000006248536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005992253,"about_ca_system_score_gemma":0.00006050164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001456489,"about_ca_topic_score_gemma":0.000005693797,"domain_scores_codex":[0.9988152,0.00002040803,0.0005121162,0.00009359821,0.0003608697,0.0001977897],"domain_scores_gemma":[0.9993485,0.0000476039,0.0001063214,0.0003377555,0.0001113045,0.00004854455],"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":[0.000305939,0.000420341,0.03193347,0.004604706,0.0001043504,0.00001646584,0.01308885,0.009815224,0.007388942,0.2189404,0.009799596,0.7035818],"study_design_scores_gemma":[0.0009560005,0.00009284994,0.004776335,0.0004839669,0.000001660749,0.000007505781,0.0005724533,0.8255023,0.01767325,0.000118332,0.1495643,0.0002510381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03761946,0.00002480069,0.9608952,0.00001236146,0.0001569154,0.000712944,0.0001438646,0.00002891566,0.0004055355],"genre_scores_gemma":[0.9781495,8.978228e-7,0.02144306,0.00002746714,0.00002638118,0.00003601036,0.0003071013,0.000002155458,0.00000738623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9405301,"threshold_uncertainty_score":0.2388691,"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."}}