{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002463539,0.00005749502,0.00006006969,0.00004851508,0.00006076513,0.0001814346,0.0005329148,0.00001779666,0.00002504006],"category_scores_gemma":[0.00001951863,0.00004761525,0.00002759053,0.0001507324,0.000008890927,0.0007134874,0.0002136564,0.0000275246,0.0000634889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001156268,"about_ca_system_score_gemma":0.000008606159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000154933,"about_ca_topic_score_gemma":0.000003308918,"domain_scores_codex":[0.9994149,0.00000602218,0.00009074294,0.0001926298,0.0001052782,0.000190483],"domain_scores_gemma":[0.9996312,0.00002648225,0.00002469509,0.0002616172,0.0000224261,0.0000336056],"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":[0.000006784373,0.00003972892,0.00002903063,0.00001531704,0.00001764817,0.000001182456,0.00007593766,0.00004727351,0.0001176941,0.6507272,0.02653242,0.3223898],"study_design_scores_gemma":[0.0004074863,0.00003831659,0.0001555756,0.000004790939,0.000004720344,0.00000110072,0.00001308052,0.6643015,0.005728474,0.005182683,0.3240005,0.0001618054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005766907,0.00002442374,0.981966,0.002064877,0.0002162938,0.0001380323,0.000002127299,0.0001945188,0.01481699],"genre_scores_gemma":[0.07918219,0.00000795792,0.9029281,0.0008908557,0.00032846,0.000009932443,0.0000184163,0.000009060574,0.01662503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6642542,"threshold_uncertainty_score":0.1941694,"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."}}