{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004877389,0.0001374724,0.0001802799,0.0001027659,0.0002508109,0.0003700923,0.001545215,0.00008527813,0.0001221893],"category_scores_gemma":[0.00002273113,0.0001002718,0.0000821737,0.0002316782,0.00002309617,0.001107657,0.0007941538,0.000091137,0.00002838397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002084975,"about_ca_system_score_gemma":0.0000438384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005783558,"about_ca_topic_score_gemma":0.00001865031,"domain_scores_codex":[0.9986456,0.0000180276,0.0002735283,0.0004073925,0.0003187593,0.0003366967],"domain_scores_gemma":[0.9988042,0.0002631874,0.00009403731,0.0005851518,0.0001155151,0.0001378981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002865388,0.0002727135,0.003673015,0.00003566215,0.00003241003,0.00002036813,0.0004625191,0.00008837215,0.001727694,0.06691426,0.2025249,0.7239616],"study_design_scores_gemma":[0.006482041,0.0001314281,0.01533926,0.00006703009,0.00000801448,0.0000125242,0.00002397683,0.2748137,0.02670573,0.01537194,0.66051,0.0005342901],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001460206,0.00007210833,0.9846515,0.0005117989,0.0006783282,0.0003377961,0.000008232999,0.0001722182,0.01210781],"genre_scores_gemma":[0.5287747,0.00004719851,0.4556264,0.005965334,0.00159044,0.00005191449,0.00004436044,0.0000405372,0.007859073],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7234273,"threshold_uncertainty_score":0.4088964,"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."}}