{"id":"W2112064847","doi":"","title":"Indexing mixed types for approximate retrieval","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Search engine indexing; Computer science; Trie; Edit distance; Categorical variable; String (physics); Data mining; Access method; Inverted index; Data structure; Theoretical computer science; Information retrieval; Algorithm; Mathematics; Database; Machine learning","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":[0.006229267,0.0008236066,0.002296787,0.004500952,0.001826685,0.007116322,0.003174043,0.002160733,0.01106071],"category_scores_gemma":[0.03339282,0.0007859598,0.001705649,0.01144356,0.002632633,0.01632532,0.005963626,0.002615792,0.005216136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001881983,"about_ca_system_score_gemma":0.002372125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001187152,"about_ca_topic_score_gemma":0.001274606,"domain_scores_codex":[0.9908946,0.002172159,0.001305763,0.000927341,0.004285431,0.0004147899],"domain_scores_gemma":[0.9756544,0.007337343,0.001388572,0.01206491,0.003242279,0.000312492],"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":[0.00045756,0.0001279738,0.001093948,0.0005834393,0.00007545179,0.0002253001,0.000678523,0.01648593,0.006088187,0.5550918,0.01209279,0.4069991],"study_design_scores_gemma":[0.0001083981,0.0002157007,0.00033512,0.0001986272,0.00008388104,0.001029646,0.0004436913,0.1906555,0.01241547,0.707204,0.08719643,0.0001135285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004242754,0.0007716419,0.9886088,0.0003608417,0.0001536692,0.0001923712,0.0003605357,0.000817811,0.004491536],"genre_scores_gemma":[0.08414154,0.001267496,0.9041572,0.000458573,0.0003091287,0.0009248445,0.001768555,0.000503662,0.00646893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01106071,"threshold_uncertainty_score":0.03700179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02231249144338153,"score_gpt":0.254048192522594,"score_spread":0.2317357010792125,"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."}}