{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009223762,0.0002578805,0.0004018,0.0001787551,0.00008867451,0.00008319749,0.001778964,0.0002744256,0.00001411026],"category_scores_gemma":[0.0001246718,0.0002469077,0.00008721308,0.0002288036,0.00005504509,0.0004056112,0.003515538,0.0006660339,0.000005868232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001021877,"about_ca_system_score_gemma":0.0003343238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001874356,"about_ca_topic_score_gemma":0.00001868996,"domain_scores_codex":[0.9976507,0.0001145297,0.000485833,0.0008746466,0.0004353361,0.0004388923],"domain_scores_gemma":[0.998012,0.00006761948,0.000139551,0.001566613,0.000109157,0.0001050791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001490445,0.001761094,0.8883997,0.003289875,0.0002847533,0.0001423561,0.001117281,0.002185447,0.01527541,0.005998481,0.007368197,0.07402837],"study_design_scores_gemma":[0.00388786,0.0005166846,0.3156332,0.005621723,0.00006609254,0.00001315193,0.0001214783,0.3465067,0.2425513,0.01415251,0.06759927,0.003330029],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6455237,0.0002045513,0.3520169,0.0001018638,0.0002845752,0.001173076,0.0005629726,0.00004352756,0.00008888153],"genre_scores_gemma":[0.8609105,0.00003499713,0.1374112,0.0001196631,0.00008121163,0.0002439449,0.001110862,0.00002563096,0.00006195087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5727665,"threshold_uncertainty_score":0.9999983,"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."}}