{"id":"W2010916971","doi":"10.1145/1132863.1132868","title":"Integrating XML data sources using approximate joins","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Joins; XML validation; XML; Efficient XML Interchange; Document Structure Description; XML Schema (W3C); XML database; Information retrieval; Streaming XML; Data mining; Set (abstract data type); Tree (set theory); XML Encryption; Database; Programming language; World Wide Web","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":[0.0006450247,0.0002356194,0.0002258399,0.0002625086,0.0004441542,0.0007688176,0.003412124,0.00004464581,0.00001553283],"category_scores_gemma":[0.00002580177,0.0002090692,0.00005082696,0.0006086887,0.00004508615,0.002746512,0.0002513643,0.0002173363,0.00006603077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004848087,"about_ca_system_score_gemma":0.00004260462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002600541,"about_ca_topic_score_gemma":0.0001590475,"domain_scores_codex":[0.9978706,0.0001120941,0.0004257681,0.0007860456,0.0004300545,0.0003754994],"domain_scores_gemma":[0.9952618,0.0001096217,0.0001502299,0.004366148,0.00003814234,0.00007399989],"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":[0.0001025569,0.005205174,0.001317388,0.003004951,0.001396839,0.000913572,0.001599835,0.1140444,0.02703342,0.2612251,0.04833811,0.5358188],"study_design_scores_gemma":[0.0003427732,0.00002752211,0.00001754675,0.0002035477,0.00004436975,0.00004203835,0.0003099292,0.9748998,0.0006996151,0.000152731,0.02291302,0.0003471658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001312555,0.0001553828,0.9946947,0.000175082,0.001001512,0.0003352186,0.001369839,0.0003665092,0.0005892667],"genre_scores_gemma":[0.4233841,0.00004943761,0.5715017,0.0001571371,0.0006029073,0.00006935373,0.002692138,0.0000648788,0.001478331],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8608554,"threshold_uncertainty_score":0.8525596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06748389564404962,"score_gpt":0.2828255905583581,"score_spread":0.2153416949143085,"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."}}