{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005937943,0.0001184956,0.0001551279,0.0004482252,0.00007559639,0.000465679,0.0005679903,0.00005100502,0.00001542854],"category_scores_gemma":[0.00003178,0.00009693004,0.0000305133,0.001840076,0.00001422447,0.0008037492,0.0001855421,0.0001464981,0.0001791957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001682505,"about_ca_system_score_gemma":0.00009797532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006081023,"about_ca_topic_score_gemma":0.000005542781,"domain_scores_codex":[0.9982157,0.00007006828,0.0004209343,0.0002409673,0.0006259906,0.0004263072],"domain_scores_gemma":[0.9993774,0.00004630309,0.00006371542,0.0002993821,0.00009726055,0.0001159232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001310144,0.0009446028,0.03949077,0.0003467866,0.0000204919,0.00007653835,0.005873256,0.06617916,0.0005810781,0.8537304,0.01080534,0.02182061],"study_design_scores_gemma":[0.001714363,0.0001734378,0.05089711,0.00005656174,0.0000043026,0.00004152085,0.0006535726,0.9365571,0.0006577121,0.0006479091,0.008030144,0.0005663071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1624321,0.0000334176,0.7971647,0.0002527313,0.0002112937,0.0008631374,0.00000150041,0.000173594,0.03886753],"genre_scores_gemma":[0.987642,0.000001258178,0.008316522,0.0001741157,0.00002799072,0.00002080452,0.000005347029,0.000005220236,0.003806765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8703779,"threshold_uncertainty_score":0.4490553,"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."}}