{"id":"W2135290016","doi":"10.1145/1183614.1183644","title":"A document-centric approach to static index pruning in text retrieval systems","year":2006,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pruning; Index (typography); Information retrieval; Divergence (linguistics); Document retrieval; Term (time); Language model; Artificial intelligence; Inverted index; Natural language processing; Search engine indexing; World Wide Web","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":[0.002815365,0.0009695852,0.001774536,0.003885181,0.001842325,0.002865553,0.00271664,0.00141042,0.001658016],"category_scores_gemma":[0.01278267,0.0008320152,0.0008690779,0.004778752,0.001357984,0.004756206,0.001949407,0.001743752,0.001355169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001075645,"about_ca_system_score_gemma":0.001731645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002183187,"about_ca_topic_score_gemma":0.003832059,"domain_scores_codex":[0.9966876,0.0008433207,0.0003547373,0.0004239787,0.00151047,0.0001798309],"domain_scores_gemma":[0.9912121,0.003351066,0.0006340862,0.002636355,0.001956139,0.0002102512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003842384,0.0003273659,0.002754325,0.0005539028,0.0001399678,0.0004384342,0.0008155603,0.032418,0.07409833,0.02683641,0.01301129,0.8482222],"study_design_scores_gemma":[0.0001736978,0.0006919863,0.003735792,0.0001725408,0.000405806,0.002152455,0.0003003472,0.7402562,0.1253235,0.07211211,0.05444859,0.000227053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02154746,0.002089771,0.9682657,0.0004204111,0.00008796555,0.0002766831,0.0001945363,0.004208006,0.002909519],"genre_scores_gemma":[0.1562488,0.0009960176,0.8369401,0.0003063719,0.0002829506,0.0003504014,0.0007143657,0.0004750119,0.00368612],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003885181,"threshold_uncertainty_score":0.01488924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01364077173481446,"score_gpt":0.2435377339678875,"score_spread":0.229896962233073,"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."}}