{"id":"W3114259864","doi":"10.1109/bdcat50828.2020.00019","title":"A Data Indexing Technique to Improve the Search Latency of AND Queries for Large Scale Textual Documents","year":2020,"lang":"en","type":"article","venue":"","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Telus (Canada); Carleton University","funders":"","keywords":"Search engine indexing; Computer science; Inverted index; Latency (audio); Workload; Graph; Search engine; Hash function; Data mining; Hash table; Information retrieval; Theoretical computer science; Operating system","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":[0.000394747,0.00005835857,0.00008792999,0.00002354196,0.0000912347,0.00009122123,0.0008616491,0.00002223251,0.000002886175],"category_scores_gemma":[0.00005346734,0.00003848421,0.00001822853,0.0001336949,0.00001856789,0.0003833346,0.001361827,0.00007321441,0.000002125334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004678719,"about_ca_system_score_gemma":0.00003411804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001534292,"about_ca_topic_score_gemma":0.00004776918,"domain_scores_codex":[0.9993063,0.00002478264,0.0001170019,0.0002723892,0.000130683,0.0001489092],"domain_scores_gemma":[0.9993648,0.00007144467,0.00002146728,0.0004365796,0.00004623057,0.00005945693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003116656,0.0003052094,0.0116818,0.0004515649,0.0001891208,0.00001284723,0.02317645,0.00004677831,0.3861156,0.3162504,0.02634243,0.2351161],"study_design_scores_gemma":[0.001992268,0.001779668,0.001935352,0.0001442958,0.00003611511,0.0000197841,0.004915108,0.8829165,0.06819388,0.003669373,0.03364727,0.0007504434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03370282,0.00004174128,0.959881,0.00521849,0.00003231713,0.0004815623,0.00007687069,0.00006182001,0.0005033984],"genre_scores_gemma":[0.981524,0.00000550376,0.0170279,0.00112301,0.0000273525,0.00002771448,0.000004092793,0.000003929068,0.000256528],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9478211,"threshold_uncertainty_score":0.169742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04571766267515183,"score_gpt":0.3017729559559621,"score_spread":0.2560552932808103,"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."}}