{"id":"W2061022164","doi":"10.1145/1451940.1451960","title":"A bottom-up approach for XML documents classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Document Structure Description; Information retrieval; XML; SGML; XML Schema Editor; XML validation; Efficient XML Interchange; Document type definition; XML Schema (W3C); XML database; Schema (genetic algorithms); 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":[0.0001632362,0.00006279134,0.00008526846,0.00006585728,0.0001460791,0.00007085428,0.0005153536,0.00003355727,0.000005892599],"category_scores_gemma":[0.00002275499,0.0000508667,0.00005678889,0.00025232,0.00002022433,0.0003879709,0.00006583751,0.00004252049,0.00005583675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001433274,"about_ca_system_score_gemma":0.00003418401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002810469,"about_ca_topic_score_gemma":7.187256e-7,"domain_scores_codex":[0.999267,0.00001682944,0.0001219195,0.0002880272,0.0001627706,0.0001434249],"domain_scores_gemma":[0.9993804,0.0000256276,0.00004309814,0.0004508593,0.00005048006,0.00004960662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001533278,0.0004782266,0.005645643,0.00004164746,0.0001721088,0.000003123592,0.002012944,0.000108245,0.005152064,0.1501452,0.7598965,0.07632894],"study_design_scores_gemma":[0.0005763922,0.0000558225,0.002362661,0.000003479372,0.00001754014,0.0000164317,0.0001139114,0.9484417,0.001347937,0.0006114184,0.04620669,0.0002460462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002740442,0.00001358843,0.9850686,0.0002997225,0.0001755956,0.00007498398,0.000002606223,0.0001201004,0.01150433],"genre_scores_gemma":[0.5687224,0.00001132429,0.4181013,0.0002320043,0.0001409672,0.00004686376,0.00005198293,0.000004305679,0.01268888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9483334,"threshold_uncertainty_score":0.2074284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0649444665900192,"score_gpt":0.2806387728962791,"score_spread":0.2156943063062599,"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."}}