{"id":"W2102247866","doi":"10.1109/dexa.2006.62","title":"Finding Syntactic Similarities Between XML Documents","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; XML; Document Structure Description; Edit distance; XML validation; Information retrieval; Tree (set theory); Efficient XML Interchange; Simple API for XML; Tree structure; XML Schema (W3C); XML database; Document type definition; Theoretical computer science; Data mining; XML Signature; Algorithm; Programming language; Data structure; World Wide Web; Mathematics","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":[0.001716031,0.0006028794,0.0009629435,0.008699205,0.0009023353,0.002165242,0.001282586,0.001156978,0.002955035],"category_scores_gemma":[0.01501985,0.0005214703,0.001111854,0.005703525,0.0004721066,0.004311577,0.001676171,0.0008222046,0.001131185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007712436,"about_ca_system_score_gemma":0.001377745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001031652,"about_ca_topic_score_gemma":0.001650325,"domain_scores_codex":[0.9973239,0.0005366299,0.0004343155,0.0005813286,0.0009951399,0.0001287817],"domain_scores_gemma":[0.9915056,0.003942763,0.001541454,0.001098691,0.001698444,0.0002131514],"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":[0.0009921003,0.0004635704,0.03198187,0.00251759,0.0004667057,0.002059919,0.00249777,0.01432185,0.06203843,0.04768426,0.009939002,0.825037],"study_design_scores_gemma":[0.0003875901,0.00224416,0.0905733,0.001087754,0.001523114,0.009150766,0.006060553,0.3935213,0.1612509,0.1861456,0.1476768,0.0003780359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3088913,0.003232694,0.6634266,0.0008596503,0.0002670969,0.0009052391,0.008296332,0.00571312,0.008407887],"genre_scores_gemma":[0.4698904,0.00130883,0.5128086,0.0001798145,0.0001918557,0.0003214004,0.01238715,0.0004430025,0.002468929],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008699205,"threshold_uncertainty_score":0.009885609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01781436096921012,"score_gpt":0.2641840172389015,"score_spread":0.2463696562696914,"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."}}