{"id":"W1967654850","doi":"10.14778/1687627.1687642","title":"Measure-driven keyword-query expansion","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Exploit; Pruning; Information retrieval; Query expansion; Web search query; Context (archaeology); Set (abstract data type); Process (computing); Domain (mathematical analysis); Measure (data warehouse); Focus (optics); Query optimization; Data mining; Word (group theory); Search engine; 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":[0.0002935311,0.0001393855,0.0001494762,0.00008458587,0.0001119967,0.0001472671,0.001748166,0.00002931721,0.000006334734],"category_scores_gemma":[0.00003477958,0.00009365909,0.0000966987,0.0003897801,0.00003013505,0.0007735371,0.0005429788,0.00009895483,0.00001876442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004130773,"about_ca_system_score_gemma":0.00001441846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008529801,"about_ca_topic_score_gemma":4.455152e-7,"domain_scores_codex":[0.9986631,0.000005310395,0.000224387,0.0003098115,0.0005431836,0.0002541723],"domain_scores_gemma":[0.9993754,0.00001034016,0.0001691406,0.0002786747,0.00011066,0.00005576828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003094124,0.0005921095,0.002095034,0.00009043943,0.00008663569,0.000003618088,0.001552596,0.00004895161,0.1176315,0.4068808,0.05600084,0.4149866],"study_design_scores_gemma":[0.003873311,0.001230376,0.04921186,0.001009819,0.0001691524,0.00004342072,0.0005796009,0.03699951,0.7104551,0.111289,0.08345318,0.001685669],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.379091,0.00157436,0.09173287,0.09179708,0.005961207,0.006264667,0.00002768294,0.002440848,0.4211103],"genre_scores_gemma":[0.9787016,0.00004786812,0.01962393,0.0006738421,0.00009143847,0.00001476848,8.436865e-7,0.000006589869,0.0008391563],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5996106,"threshold_uncertainty_score":0.3819307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0125232210154417,"score_gpt":0.212247243297686,"score_spread":0.1997240222822443,"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."}}