{"id":"W2147671191","doi":"10.1145/1148170.1148233","title":"Hybrid index maintenance for growing text collections","year":2006,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Search engine indexing; Computer science; Merge (version control); Index (typography); Monotonic function; Auxiliary memory; Information retrieval; Zipf's law; Data mining; World Wide Web; Mathematics; Statistics","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":[0.00008312704,0.0000674373,0.00007185999,0.0000616714,0.0003108911,0.0001697122,0.0003618243,0.00001768051,0.00001944109],"category_scores_gemma":[0.00001554268,0.00005369847,0.00003750657,0.0002776321,0.00001414856,0.0006049286,0.0001435444,0.00004237726,0.00001511934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002537304,"about_ca_system_score_gemma":0.00003710734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002751419,"about_ca_topic_score_gemma":0.00001792294,"domain_scores_codex":[0.9993433,0.000008037691,0.0001193916,0.0002325068,0.0001008853,0.0001959213],"domain_scores_gemma":[0.9995163,0.00005972237,0.00003023958,0.0002827022,0.00007844979,0.00003259034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005037047,0.00007217284,0.0001386096,0.000006055611,0.000005033813,0.000005758692,0.00001124856,0.0006419922,0.0006105067,0.2702837,0.6997905,0.0284294],"study_design_scores_gemma":[0.0004306765,0.00003803936,0.0008787984,0.00001353354,0.000001753639,0.00002571631,0.000007676896,0.6496998,0.003185963,0.03644252,0.3091213,0.0001542996],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004811671,0.00002522689,0.9835436,0.0005522105,0.0003022687,0.0001283916,0.000008362413,0.0001566711,0.01480208],"genre_scores_gemma":[0.4739743,0.000005311184,0.4738154,0.0009180824,0.0003497988,0.00009376296,0.00002102084,0.0000138782,0.0508085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6490578,"threshold_uncertainty_score":0.2391154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008690065081308028,"score_gpt":0.22291227247964,"score_spread":0.2142222073983319,"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."}}