{"id":"W2291149938","doi":"10.1137/1.9781611973754.2","title":"A Data-Aware FM-index","year":2014,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Search engine indexing; Computer science; Code (set theory); Index (typography); Algorithm; Wavelet; Data compression; Entropy (arrow of time); Tree (set theory); Theoretical computer science; Wavelet transform; Data mining; Artificial intelligence; Mathematics","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":[0.0005709008,0.0004641898,0.0006746121,0.00003686437,0.0003430469,0.0003129735,0.001616065,0.0008375549,0.00001388778],"category_scores_gemma":[0.00001225996,0.0003833711,0.0002847844,0.00001585855,0.0001414735,0.00007602514,0.001924163,0.0005640537,0.00001649706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003048077,"about_ca_system_score_gemma":0.0001298509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002216545,"about_ca_topic_score_gemma":0.00000138535,"domain_scores_codex":[0.9978752,0.000003396011,0.0005323238,0.0008324714,0.0004189862,0.0003375956],"domain_scores_gemma":[0.9973965,0.0002757828,0.0004658657,0.001634945,0.00006142206,0.00016554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006005173,0.00001217733,2.644394e-8,0.0001628569,0.000136922,5.440905e-7,0.0002280112,0.000001090345,0.0000141634,0.8175402,0.06082704,0.121071],"study_design_scores_gemma":[0.001148333,0.00005631922,2.551224e-8,0.0002064769,0.0001332285,0.000008015225,0.00004538445,0.03851026,0.00005250557,0.2803945,0.6788775,0.000567453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002967924,0.00004933877,0.8471339,0.00009210245,0.0003584762,0.001120714,0.0008391386,0.0001889809,0.1502144],"genre_scores_gemma":[0.0006534756,0.00007239742,0.5295983,0.001011139,0.005511278,0.0001983958,0.00175355,0.0003015308,0.4608999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6180505,"threshold_uncertainty_score":0.9998618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1035413490006835,"score_gpt":0.2667702607326768,"score_spread":0.1632289117319933,"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."}}