{"id":"W2031979200","doi":"10.1016/j.ins.2013.06.019","title":"Weighting tags and paths in XML documents according to their topic generalization","year":2013,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Weighting; Computer science; Generalization; Information retrieval; XML; Data mining; Document Structure Description; Database; Mathematics; 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":[0.000404952,0.00005500347,0.00005149661,0.0002469773,0.0001415359,0.001281286,0.0004670918,0.00001253973,0.000009738344],"category_scores_gemma":[0.00003186042,0.00004147372,0.00000703385,0.0006435154,0.0000211354,0.01209375,0.0002949823,0.00002354995,0.000110509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001427768,"about_ca_system_score_gemma":0.00001199009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001699156,"about_ca_topic_score_gemma":0.000007699987,"domain_scores_codex":[0.9993362,0.00001410335,0.0001924849,0.0001120009,0.0001963663,0.0001488608],"domain_scores_gemma":[0.9997348,0.00001917183,0.0000650013,0.0001108751,0.000033128,0.000037058],"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":[2.330448e-7,0.000005543224,0.02048262,0.00001011121,0.000001508179,2.178056e-7,0.003345554,0.0004641218,0.0001408146,0.03239468,0.0005999449,0.9425547],"study_design_scores_gemma":[0.0003101425,0.00006727011,0.06068147,0.00005028549,9.62394e-7,0.000002500927,0.002620307,0.9022223,0.0009725997,0.01028137,0.02250528,0.000285564],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6497818,0.00001475058,0.3352853,0.001729433,0.0003505766,0.0003072854,0.000001023812,0.00006720013,0.01246258],"genre_scores_gemma":[0.9781753,0.00001322888,0.02049858,0.001204605,0.00001974414,0.0000219111,0.000003725287,7.654081e-7,0.00006214893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9422691,"threshold_uncertainty_score":0.9997555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01434166746850803,"score_gpt":0.2454466806356847,"score_spread":0.2311050131671767,"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."}}