{"id":"W2040975520","doi":"10.1109/bibm.2012.6392695","title":"Efficient filtration for similarity search with spaced k-mer neighbors","year":2012,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Western University","funders":"","keywords":"Nearest neighbor search; Similarity (geometry); Seeding; Computer science; Set (abstract data type); Heuristic; Sensitivity (control systems); Algorithm; Pattern recognition (psychology); Filtration (mathematics); Speedup; Data mining; Selection (genetic algorithm); Sequence (biology); Artificial intelligence; Mathematics; Image (mathematics); Parallel computing; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001213927,0.0004251741,0.001039343,0.001361681,0.0008430271,0.0007414865,0.001029315,0.0008765871,0.0009067316],"category_scores_gemma":[0.005225891,0.0003902581,0.0004623682,0.001903066,0.0006684666,0.001536133,0.0009673139,0.0005901983,0.0005587275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005750415,"about_ca_system_score_gemma":0.0009062206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001512372,"about_ca_topic_score_gemma":0.002075928,"domain_scores_codex":[0.9989567,0.0002406669,0.0001035301,0.0001717253,0.0004583009,0.00006901459],"domain_scores_gemma":[0.9977519,0.00117869,0.0001921768,0.000433173,0.0003562815,0.00008778113],"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":[0.001184034,0.0002915449,0.0047301,0.0002582494,0.00007151384,0.0004332279,0.0005843693,0.08401175,0.1408678,0.03557174,0.004242441,0.7277532],"study_design_scores_gemma":[0.00008697289,0.0003956229,0.001409712,0.00003134995,0.00003200714,0.0006895956,0.0001092865,0.8873872,0.08469359,0.01778025,0.007308474,0.00007591874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07299726,0.0006856984,0.9242287,0.00006556362,0.00004500727,0.0000887768,0.00007122146,0.0009485143,0.0008694479],"genre_scores_gemma":[0.2865106,0.0003374788,0.7112438,0.00007673791,0.00003502853,0.0001661494,0.0003798286,0.00008777596,0.00116255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001512372,"threshold_uncertainty_score":0.006419897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02729143526162593,"score_gpt":0.2727366383145167,"score_spread":0.2454452030528908,"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."}}