{"id":"W2044014345","doi":"10.5555/1109557.1109599","title":"Rank/select operations on large alphabets: a tool for text indexing","year":2006,"lang":"en","type":"article","venue":"Symposium on Discrete Algorithms","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Search engine indexing; Rank (graph theory); Generalization; String (physics); Variety (cybernetics); Computer science; Representation (politics); Alphabet; Combinatorics; Binary number; Binary search algorithm; Theoretical computer science; Mathematics; Algorithm; Information retrieval; Search algorithm; Artificial intelligence; Arithmetic","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004621488,0.0003986147,0.0003465864,0.0002276178,0.0007731514,0.0005946356,0.001088927,0.0001568163,0.00002903456],"category_scores_gemma":[0.00003810518,0.0003288819,0.0002052313,0.000460554,0.00004312114,0.0009085161,0.0002862464,0.0002693249,0.0001281529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078982,"about_ca_system_score_gemma":0.0001046873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001057569,"about_ca_topic_score_gemma":0.00002218427,"domain_scores_codex":[0.9970716,0.00009971038,0.0004888374,0.0009739427,0.0005790313,0.0007869253],"domain_scores_gemma":[0.9983193,0.0002199132,0.0001075594,0.001083206,0.0001405232,0.000129444],"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":[0.0003387009,0.002317634,0.0003193447,0.0001334883,0.0002374163,0.0001054098,0.001138558,0.03625705,0.03504686,0.713357,0.08281572,0.1279328],"study_design_scores_gemma":[0.003038549,0.001304524,0.0008025909,0.0001681269,0.00002868795,0.00001756974,0.00002950123,0.9078004,0.01573731,0.003731263,0.06640255,0.0009389583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003877284,0.0001458977,0.9877126,0.002408786,0.0008979346,0.0009985911,0.0003434785,0.0003987123,0.003216733],"genre_scores_gemma":[0.6749784,0.0001077132,0.3080802,0.004397094,0.002994128,0.00124882,0.001201826,0.0001967221,0.006795134],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8715433,"threshold_uncertainty_score":0.9999163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008969900852929844,"score_gpt":0.2570800764681503,"score_spread":0.2481101756152204,"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."}}