{"id":"W2950820003","doi":"10.48550/arxiv.cs/0309005","title":"Indexing Schemes for Similarity Search In Datasets of Short Protein Fragments","year":2003,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fonterra Co-Operative Group; Victoria University; Victoria University of Wellington; University of Ottawa","keywords":"Search engine indexing; Nearest neighbor search; Similarity (geometry); Block (permutation group theory); Computer science; Alphabet; Pattern recognition (psychology); Fragment (logic); Data mining; Artificial intelligence; Algorithm; Mathematics; Combinatorics; Image (mathematics)","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":[0.003617445,0.0005698365,0.001452249,0.004935851,0.001198486,0.001701245,0.002987021,0.001124418,0.002530305],"category_scores_gemma":[0.01821656,0.0004107007,0.0008450513,0.008309823,0.001070608,0.004632663,0.003144949,0.001338325,0.002198133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111539,"about_ca_system_score_gemma":0.001733433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001306064,"about_ca_topic_score_gemma":0.001747823,"domain_scores_codex":[0.9956853,0.0008605358,0.0007037484,0.0005745257,0.001936794,0.0002391221],"domain_scores_gemma":[0.9895815,0.002609738,0.0009352259,0.004735469,0.001796889,0.0003412358],"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":[0.0009345412,0.0003993339,0.004624169,0.0005184657,0.0001106311,0.0001510899,0.0004972772,0.03557894,0.04437339,0.05430775,0.01609499,0.8424094],"study_design_scores_gemma":[0.0004202666,0.0008408528,0.004085109,0.00009492941,0.00009585149,0.001009762,0.0003386542,0.737654,0.06558101,0.1678906,0.02181856,0.0001703929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05562282,0.0008871289,0.9350026,0.0003671783,0.00008918895,0.0003612244,0.001874875,0.004510104,0.001284787],"genre_scores_gemma":[0.1756753,0.000310853,0.816346,0.0001456049,0.0001026354,0.00057875,0.005595162,0.0002355121,0.00101014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004935851,"threshold_uncertainty_score":0.01913112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09477066533544168,"score_gpt":0.3400283011467722,"score_spread":0.2452576358113305,"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."}}