{"id":"W2137339254","doi":"10.1145/1321440.1321546","title":"Index compression is good, especially for random access","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Random access; Uncompressed video; Index (typography); Computer science; Overhead (engineering); Compression (physics); Data compression; Inverted index; Data access; Information retrieval; Data mining; Database; Search engine indexing; Computer network; World Wide Web; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002154578,0.001416766,0.001664603,0.002871471,0.001713939,0.003417261,0.001483674,0.00173948,0.02259814],"category_scores_gemma":[0.01870188,0.0006225891,0.0006926853,0.006370889,0.001077235,0.006147678,0.001302124,0.001606746,0.02773243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005866731,"about_ca_system_score_gemma":0.0009600149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001006146,"about_ca_topic_score_gemma":0.001272076,"domain_scores_codex":[0.9963315,0.0004101572,0.0003108209,0.0005067713,0.002217115,0.0002235996],"domain_scores_gemma":[0.9855439,0.004585114,0.0009588557,0.00409195,0.004539601,0.0002805794],"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":[0.0008432279,0.0002701094,0.003941985,0.001316769,0.0001900827,0.000741614,0.0002469285,0.006512981,0.04589546,0.01778511,0.08893185,0.8333238],"study_design_scores_gemma":[0.0004934978,0.001640228,0.01813164,0.0008834134,0.0005480815,0.01513073,0.0006086137,0.05592962,0.2242553,0.1103694,0.5716023,0.0004070778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05312664,0.04849071,0.7228062,0.01210578,0.003772535,0.0008417743,0.00548726,0.03706142,0.1163077],"genre_scores_gemma":[0.3627079,0.02292094,0.5052341,0.005198659,0.00641661,0.0006172795,0.01105621,0.006880934,0.07896731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02259814,"threshold_uncertainty_score":0.07559836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02805789760268694,"score_gpt":0.3251836736894811,"score_spread":0.2971257760867941,"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."}}