{"id":"W1977733667","doi":"10.1093/comjnl/bxt106","title":"A New and Effective Approach to GML Documents Compression","year":2013,"lang":"en","type":"article","venue":"The Computer Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; XML; Compression ratio; Information retrieval; Data mining; Compression (physics); Encoding (memory); Tree (set theory); Data compression; Pattern matching; Database; Artificial intelligence; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003360964,0.0001197151,0.0001198979,0.00008486612,0.0002563944,0.001434451,0.001249361,0.00001770231,0.00001392194],"category_scores_gemma":[0.0000034395,0.00006944831,0.00003470081,0.0001805256,0.00001683601,0.001055661,0.001263084,0.0001968431,0.0001408666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001828275,"about_ca_system_score_gemma":0.00001120746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002614964,"about_ca_topic_score_gemma":1.471847e-7,"domain_scores_codex":[0.9990271,0.0001150899,0.0001432705,0.0002176452,0.0002519844,0.0002449551],"domain_scores_gemma":[0.9992854,0.00005468804,0.00006827922,0.0003377617,0.00003967841,0.0002141769],"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":[0.000002135051,0.00002676965,0.00008292088,0.000003406203,0.00002998469,0.000003366174,0.0006098746,0.0001514362,0.00003376102,0.003638287,0.1414662,0.8539518],"study_design_scores_gemma":[0.002384032,0.0005288522,0.0760899,0.0001490973,0.00003288341,0.0007084245,0.00005774297,0.7988216,0.000176198,0.05135133,0.06906,0.0006399977],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00461835,0.00007090749,0.9902228,0.002208014,0.000582769,0.0003731583,2.469271e-7,0.00004418313,0.00187963],"genre_scores_gemma":[0.08876356,0.00002942933,0.9053482,0.003278306,0.001238232,0.00002288857,0.000001744753,0.00001348628,0.001304131],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8533118,"threshold_uncertainty_score":0.9996021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008118702872697147,"score_gpt":0.2224352901072514,"score_spread":0.2143165872345542,"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."}}