{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002819741,0.00008195196,0.00007627662,0.00003873718,0.0001614525,0.00008885265,0.0002741255,0.00003501986,0.00003737326],"category_scores_gemma":[0.00001118153,0.00005269291,0.00002451742,0.0001597643,0.0000214597,0.000325161,0.000124025,0.00006206915,0.00002102136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001895209,"about_ca_system_score_gemma":0.0000356602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004271124,"about_ca_topic_score_gemma":0.00000524512,"domain_scores_codex":[0.9991659,0.00002396818,0.00008394976,0.000197469,0.0002354838,0.0002932214],"domain_scores_gemma":[0.9993413,0.00007802589,0.00002529438,0.0003624808,0.00007525423,0.0001176441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002341058,0.001890727,0.01503509,0.0001290281,0.00008638104,0.000005848607,0.004977276,0.03015114,0.008626774,0.74866,0.04867006,0.1415336],"study_design_scores_gemma":[0.0004093448,0.0001259223,0.008101571,0.00000898322,0.000004001707,0.00000503207,0.00004525067,0.9773778,0.007265533,0.00009917723,0.0064015,0.000155927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01972171,0.00003048538,0.9774711,0.0006910944,0.0001649125,0.0002450984,0.000005923637,0.00008904286,0.001580617],"genre_scores_gemma":[0.6892011,9.069726e-7,0.3101358,0.0002066952,0.0001021634,0.00001799765,0.0000119791,0.000005286885,0.0003181043],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9472266,"threshold_uncertainty_score":0.2148755,"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."}}