{"id":"W2087413773","doi":"10.1002/spe.724","title":"Declarative generation of synthetic XML data","year":2006,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Calgary","funders":"","keywords":"Computer science; XML; Benchmarking; XML Schema (W3C); Programming language; Schema (genetic algorithms); Synthetic data; Generator (circuit theory); Software engineering; XML validation; Information retrieval; Artificial intelligence; World Wide Web; Document type definition","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":[0.0002193505,0.00009324721,0.0001200808,0.00003190455,0.0001429175,0.00005549479,0.000359246,0.00003028663,0.000005007057],"category_scores_gemma":[0.0006762092,0.00008070316,0.00001105786,0.0001720179,0.0001084024,0.004270916,0.0003914694,0.00006028296,0.000006086743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008933038,"about_ca_system_score_gemma":0.00004865013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003229527,"about_ca_topic_score_gemma":0.00003697963,"domain_scores_codex":[0.9989845,0.00007050714,0.0002130926,0.0003976343,0.0001989698,0.0001352614],"domain_scores_gemma":[0.9985511,0.0002622482,0.000180247,0.0008570303,0.0001133704,0.00003595441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006629788,0.0004229653,0.00303716,0.0001243269,0.0000427469,0.0001146883,0.02256883,0.0002886569,0.02914552,0.7895699,0.004977237,0.1496417],"study_design_scores_gemma":[0.0008422127,0.0003745796,0.001628152,0.0001916448,0.00005181525,0.0006817123,0.009731404,0.03753174,0.07831656,0.003563446,0.8659395,0.001147218],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0192124,0.001160159,0.9786659,0.0003202941,0.0001557229,0.0000934223,0.00002300463,0.00005969547,0.0003093994],"genre_scores_gemma":[0.4821839,0.0001038347,0.5173645,0.0001422177,0.00008088006,0.00001882537,0.0000328378,0.000004928969,0.0000680161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8609623,"threshold_uncertainty_score":0.329098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05494910959855257,"score_gpt":0.3188442579609946,"score_spread":0.263895148362442,"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."}}