{"id":"W2127094475","doi":"10.1007/s10115-004-0189-y","title":"Optimizing complex queries based on similarities of subqueries","year":2005,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"IBM (Canada)","funders":"International Business Machines Corporation","keywords":"Computer science; Query optimization; Joins; Key (lock); Similarity (geometry); Information retrieval; Graph; Database; Query expansion; Query language; Data mining; Theoretical computer science; Artificial intelligence","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":[0.0002731897,0.0000906757,0.0001426722,0.0001897574,0.0001014027,0.0003011597,0.0002427668,0.00002812802,0.000006860899],"category_scores_gemma":[0.000016058,0.00007848248,0.00002372138,0.0001627836,0.00004474297,0.004762053,0.00009901288,0.00003777944,0.00004626101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001570091,"about_ca_system_score_gemma":0.00002126401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009567724,"about_ca_topic_score_gemma":0.000003099133,"domain_scores_codex":[0.9993129,0.00003095977,0.0003197676,0.00007807141,0.0001455482,0.0001127904],"domain_scores_gemma":[0.999452,0.00005079521,0.0001224506,0.0002335932,0.0001075677,0.00003361402],"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":[0.00001665493,0.00006852196,0.0003000665,0.0007984497,0.00002617411,4.819233e-7,0.01020154,0.004699821,0.00002766517,0.8459261,0.02210415,0.1158304],"study_design_scores_gemma":[0.0002165996,0.00004693391,0.0003352866,0.00005466639,0.000001937417,8.493361e-7,0.0004038877,0.5573569,0.0001851289,0.000011694,0.4413024,0.00008376533],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001327747,0.0005001866,0.7749097,0.0006134908,0.0005396666,0.0003584072,0.00004173606,0.0002256195,0.2214835],"genre_scores_gemma":[0.9839904,0.00004368242,0.01516439,0.0002709495,0.00008545162,0.00001986077,0.00005822731,0.000003390834,0.0003636104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9826627,"threshold_uncertainty_score":0.3452373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02174929548707117,"score_gpt":0.2401478990607206,"score_spread":0.2183986035736494,"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."}}