{"id":"W2067662418","doi":"10.1145/1344411.1344415","title":"Locality-Based pruning methods for web search","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundação para a Ciência e a Tecnologia; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Pruning; Computer science; Locality; Search engine; Simple (philosophy); Reduction (mathematics); Data mining; Artificial intelligence; Phrase; Information retrieval; Machine learning; Mathematics","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":[0.0007803608,0.0001231237,0.0001614061,0.0002758024,0.0006134291,0.0001952366,0.0007324599,0.00008557871,0.000007285078],"category_scores_gemma":[0.00003529974,0.0001077008,0.00008503185,0.0004133723,0.00003292536,0.002269824,0.00001437143,0.0001507775,0.00008583968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007026043,"about_ca_system_score_gemma":0.0001860792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005921684,"about_ca_topic_score_gemma":5.169803e-7,"domain_scores_codex":[0.9987373,0.0001407791,0.0004333644,0.0001600808,0.0003066157,0.0002218903],"domain_scores_gemma":[0.9983115,0.000388803,0.0001081991,0.0008507284,0.0002421964,0.00009853535],"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":[0.00007672801,0.0001582487,0.00004330639,0.0003765487,0.00006235423,0.000001760829,0.003292443,0.2598033,0.0004504207,0.009173029,0.002256808,0.724305],"study_design_scores_gemma":[0.0005823182,0.00009048778,0.00005886447,0.00004647573,0.000003665603,0.00002187394,0.0001358675,0.8781237,0.00185503,0.00004699039,0.118897,0.0001377177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002537268,0.00002495964,0.9975249,0.0002775133,0.0007356094,0.0005037675,0.00004674932,0.0002543174,0.0003784918],"genre_scores_gemma":[0.2952612,0.00001008724,0.7039942,0.0003079106,0.00004383019,0.0002348165,0.00004506197,0.00000770541,0.00009510431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7241673,"threshold_uncertainty_score":0.4718063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0624142167311531,"score_gpt":0.3439271494300092,"score_spread":0.2815129326988561,"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."}}