{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002363927,0.001021335,0.002107982,0.003032393,0.00180413,0.003434257,0.002587882,0.001668756,0.01217717],"category_scores_gemma":[0.01411651,0.0007839616,0.001193491,0.006319441,0.00231729,0.01096172,0.003957884,0.002788253,0.006487657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008916512,"about_ca_system_score_gemma":0.001141498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001078952,"about_ca_topic_score_gemma":0.001317115,"domain_scores_codex":[0.9970132,0.0007469373,0.0002934503,0.0004142309,0.001256807,0.0002754564],"domain_scores_gemma":[0.9888911,0.005473206,0.0008113441,0.003783085,0.0006370175,0.0004041524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00143034,0.0003781518,0.0009315339,0.0005660021,0.00006503077,0.0004189219,0.0007347135,0.0274776,0.02722242,0.2494606,0.04653882,0.6447759],"study_design_scores_gemma":[0.0003437469,0.0005862836,0.0003558938,0.0001338802,0.00008465488,0.001066283,0.0003907521,0.3593096,0.04160917,0.5429303,0.05304059,0.000148868],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01379317,0.0005632254,0.971505,0.0008138574,0.0001359699,0.0001851048,0.0006931847,0.007931639,0.004378889],"genre_scores_gemma":[0.138229,0.0008171932,0.8487861,0.0005436876,0.0004914076,0.0005092109,0.001770376,0.0009471759,0.007905838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01217717,"threshold_uncertainty_score":0.04073668,"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."}}